answers_chatMGL.json

[
    {
        "guid": "94cdfd24-de94-4072-a5aa-a3a9dc953d2b",
        "model_answer": "Soit \\(f\\) une fonction paire (resp. impaire) \nposs\u00e9dant un \\(DL(n)\\) autour de \\(x_0=0\\):\n\\[ \nf(x)=a_0+a_1x+a_2x^2+\\cdots+a_nx^n+x^n\\epsilon(x)\\,.\n\\]\nMontrer que tous les coefficients d'indices \nimpairs (resp. pairs) sont nuls.\n\\begin{align*}\nf(x)=a_0+a_1x+a_2x^2+\\cdots+a_nx^n+x^n\\epsilon(x)\\,.\n\\end{align*}\n\nPour tous les coefficients d'indices \nimpairs (resp. pairs) sont nuls.\n\\begin{align*}\nf(x)=a_0+a_1x+a_2x^2+\\cdots+a_nx^n+x^n\\epsilon(x)\\,.\n\\end{align*}\n\nPour tous les coefficients d'indices \nimpairs (resp. pairs) sont nuls.\n\\begin{align*}\nf(x)=a_0+a_1x+a_2x^2+\\cdots+a_nx^n+x^n\\epsilon(x)\\,.\n\\end{align*}\n\nPour tous les coefficients d'indices \nimpairs (resp. pairs) sont nuls.\n\\begin{align*}\nf(x)=a_0+a_1x+a_2x^2+\\cdots+a_nx^n+x^n\\epsilon(x)\\,.\n"
    },
    {
        "guid": "3826e1bd-05f7-4f80-a6ad-937af83dc3e4",
        "model_answer": "The goal of the 4 following questions is to prove that the methods map and mapTr are equivalent. The\nformer is the version seen in class and is specified by the lemmas MapNil and MapCons. The later version\nis a tail-recursive version and is specified by the lemmas MapTrNil and MapTrCons.\nAll lemmas on this page hold for all x: Int, y: Int, xs: List[Int], ys: List[Int], l: List\n[Int] and f: Int => Int.\nGiven the following lemmas:\n\n(MapNil) Nil.map(f) === Nil\n(MapCons) (x :: xs).map(f) === f(x) :: xs.map(f)\n(MapTrNil) Nil.mapTr(f, ys) === ys\n(MapTrCons) (x :: xs).mapTr(f, ys) === xs.mapTr(f, ys ++ (f(x) :: Nil))\n(NilAppend) Nil ++ xs === xs\n(ConsAppend) (x :: xs) ++ ys === x :: (xs ++ ys)\nLet us first prove the following lemma:\n\n(AccOut) l.mapTr(f, y :: ys) === y :: l.mapTr(f, ys)\n\nWe prove it by induction on l.\nInduction step: l is x :: xs. Therefore, we need to prove:\n(x :: xs).mapTr(f, y :: ys) === y :: (x :: xs).mapTr(f, ys)\n\nWe name the induction hypothesis IH.\nWhat exact sequence of lemmas should we apply to rewrite the left hand-side ((x :: xs).mapTr(f, y\n:: ys)) to the right hand-side (y :: (x :: xs).mapTr(f, ys))?\n\n[asy]\nimport Control.Monad\nimport Data.List\nimport Data.Map\nimport Data.Monoid\nimport Data.Traversable\nimport qualified Data.Traversable as T\nimport Data.Traversable.Traversable\nimport qualified Data.Traversable.Traversable.Traversable.Traversable as T\nimport qualified Data.Traversable.Traversable.Traversable.Traversable.Traversable.Traversable.Traversable as T\nimport qualified Data.Traversable.Traversable.Traversable.Traversable.Traversable.Traversable.Traversable.Traversable.Traversable.Traversable.Traversable.Traversable.Traversable.Traversable.Traversable.Traversable.Traversable.Traversable.Traversable.Traversable.Traversable.Traversable.Traversable.Traversable.Traversable.Traversable.Traversable.Traversable.Traversable.Traversable.Traversable.Traversable.Traversable.Traversable.Traversable.Traversable.Traversable.Traversable.Traversable.Traversable.Traversable.Traversable.Traversable.Traversable.Traversable.Traversable."
    },
    {
        "guid": "f6f7e3a3-b63a-4f13-abbe-a2b3f74c64e5",
        "model_answer": "What is the general relation between the entanglement of a state and the violation of a Bell inequality? Entanglement is necessary but not sufficient for the violation of a Bell inequality Entanglement is sufficient but not necessary for the violation of a Bell inequality Entanglement is necessary and sufficient for the violation of a Bell inequality Entanglement is necessary and sufficient for the violation of a Bell inequality Entanglement is necessary and sufficient for the violation of a Bell inequality Entanglement is necessary and sufficient for the violation of a Bell inequality Entanglement is necessary and sufficient for the violation of a Bell inequality Entanglement is necessary and sufficient for the violation of a Bell inequality Entanglement is necessary and sufficient for the violation of a Bell inequality Entanglement is necessary and sufficient for the violation of a Bell inequality Entanglement is necessary and sufficient for the violation of a Bell inequality Entanglement is necessary and sufficient for the violation of a Bell inequality Entanglement is necessary and sufficient for the violation of a Bell inequality Entanglement is necessary and sufficient for the violation of a Bell inequality Entanglement is necessary and sufficient for the violation of a Bell inequality Entanglement is necessary and sufficient for the violation of a Bell inequality Entanglement is necessary and sufficient for the violation of a Bell inequality Entanglement is necessary and sufficient for the violation of a Bell inequality Entanglement is necessary and sufficient for the violation of a Bell inequality Entanglement is necessary and sufficient for the violation of a Bell inequality Entanglement is necessary and sufficient for the violation of a Bell inequality Entanglement is necessary and sufficient for the violation of a Bell inequality Entanglement is necessary and sufficient for the violation of a Bell inequality Entanglement is necessary and sufficient for the violation of a Bell inequality Entanglement is necessary and"
    },
    {
        "guid": "0b473eff-0fc8-4fb0-9d10-bc49d18e52e3",
        "model_answer": "Cet exercice est un bref rappel de maths, il doit vous servir de \"d\u00e9tecteur de fum\u00e9e\", c'est \n     typiquement le niveau de difficult\u00e9 que nous allons rencontrer concernant la d\u00e9rivation et l'int\u00e9gration de fonctions.\n      Calculer $F(x)$, primitive de $f(x)$ pour:\n      1. f(x)=\\cos(x)\n      2. f(x)=\frac{-3}{x^2}\n      3. f(x)=e^{2x}\n      4. f(x)=\\sin(x) \\cos(x) \n       5. f(x)=\\sin(x) \\cos(x) \n       6. f(x)=\\sin(x) \\cos(x) \n       7. f(x)=\\sin(x) \\cos(x) \n       8. f(x)=\\sin(x) \\cos(x) \n       9. f(x)=\\sin(x) \\cos(x) \n       10. f(x)=\\sin(x) \\cos(x) \n       11. f(x)=\\sin(x) \\cos(x) \n       12. f(x)=\\sin(x) \\cos(x) \n       13. f(x)=\\sin(x) \\cos(x) \n       14. f(x)=\\sin(x) \\cos(x) \n       15. f(x)=\\sin(x) \\cos(x) \n       16. f(x)=\\sin(x) \\cos(x) \n       17. f(x"
    },
    {
        "guid": "6654c2b0-4dcd-432e-9c8e-26d638afe0ef",
        "model_answer": "What is the worst case complexity of listing files in a directory? The file system implements directories as hash-tables. $O(1)$ $O(number of direntries in the directory)$ $O(size of the file system)$ $O(number of direntries in the file system)$ $O(log(number of direntries in the directory))$ $O(log(number of direntries in the file system))$ $O(log(number of direntries in the file system))$ $O(log(number of direntries in the file system))$ $O(log(number of direntries in the file system))$ $O(log(number of direntries in the file system))$ $O(log(number of direntries in the file system))$ $O(log(number of direntries in the file system))$ $O(log(number of direntries in the file system))$ $O(log(number of direntries in the file system))$ $O(log(number of direntries in the file system))$ $O(log(number of direntries in the file system))$ $O(log(number of direntries in the file system))$ $O(log(number of direntries in the file system))$ $O(log(number of direntries in the file system))$ $O(log(number of direntries in the file system))$ $O(log(number of direntries in the file system))$ $O(log(number of direntries in the file system))$ $O(log(number of direntries in the file system))$ $O(log(number of direntries in the"
    },
    {
        "guid": "202f9e3f-be4d-4b51-8789-f4eb0666690f",
        "model_answer": "When using linear regression, how do you help prevent numerical instabilities? (One or multiple answers) reduce learning rate add a regularization term remove degenerate features add more features\n\n[asy]\nimport numpy as np\nimport matplotlib.pyplot as plt\nimport matplotlib.linalg as l\nimport matplotlib.linalg.linalg2 as l2\nimport matplotlib.linalg.linalg3 as l3\nimport matplotlib.linalg.linalg4 as l4\nimport matplotlib.linalg.linalg5 as l5\nimport matplotlib.linalg.linalg6 as l6\nimport matplotlib.linalg.linalg7 as l7\nimport matplotlib.linalg.linalg8 as l8\nimport matplotlib.linalg.linalg9 as l9\nimport matplotlib.linalg.linalg10 as l10\nimport matplotlib.linalg.linalg11 as l11\nimport matplotlib.linalg.linalg12 as l12\nimport matplotlib.linalg.linalg13 as l13\nimport matplotlib.linalg.linalg14 as l14\nimport matplotlib.linalg.linalg15 as l15\nimport matplotlib.linalg.linalg16 as l16\nimport matplotlib.linalg.linal"
    },
    {
        "guid": "198d8637-b6eb-4a3a-92c0-6baad4f34a2e",
        "model_answer": "Voici, en guise de r\u00e9visions, un exercice plus ambitieux s\u2019int\u00e9ressant au stockage d\u2019un fichier de musique sur un disque dur.\n\nNotre fichier de musique est lui-m\u00eame stock\u00e9 dans un r\u00e9pertoire, par exemple dans /home/muche/Musique.\n\nSupposons que du point de vue du disque, les r\u00e9pertoires sont simplement des fichiers particuliers contenant les tables des fichiers qu\u2019ils contiennent :\n  \u2014 le r\u00e9pertoire racine (/) est un fichier contenant les tables de ses fichiers et r\u00e9pertoires, dont celle du r\u00e9pertoire home ;\n  \u2014 le r\u00e9pertoire home est un fichier contenant les tables de ses fichiers et r\u00e9pertoires, dont celle du r\u00e9pertoire muche\n  \u2014...\n  \u2014 le r\u00e9pertoire Musique est un fichier contenant les tables de ses fichiers et r\u00e9pertoires, dont celle de notre fichier (donn\u00e9e plus haut).\n\nSi l\u2019on suppose que notre fichier est le seul dans le r\u00e9pertoire Musique, combien de blocs utilise alors ce r\u00e9pertoire?\n\nEn supposant ces blocs (ceux du r\u00e9petoire Musique) stock\u00e9s \u00e0 partir de l\u2019adresse 42, et en supposant que le r\u00e9pertoire muche commence par r\u00e9pr\u00e9senter les informations du r\u00e9pertoire Musique, quel est le d\u00e9but du fichier repr\u00e9sentant le r\u00e9pertoire muche?\n\nSi l\u2019on suppose que notre fichier est le seul dans le r\u00e9pertoire Musique, combien de blocs utilise alors ce r\u00e9pertoire?\n\nSi l\u2019on suppose que notre fichier est le seul dans le r\u00e9pertoire Musique, combien de blocs utilise alors ce r\u00e9pertoire?\n\nSi l\u2019on suppose que notre fichier est le seul dans le r\u00e9pertoire Musique, combien de blocs utilise alors ce r\u00e9pertoire?\n\nSi l\u2019on suppose que notre fichier est le seul dans le r\u00e9pertoire Musique, combien de blocs utilise alors ce r\u00e9pertoire?\n\nSi l\u2019on suppose que notre fichier est le seul dans le r\u00e9pertoire Musique, combien de blocs utilise alors ce r\u00e9pertoire?\n\nSi l\u2019on suppose que notre fichier est le seul dans le r\u00e9pertoire Musique, combien de blocs utilise alors ce r\u00e9pertoire?\n\nSi l\u2019on suppose que notre fichier est le seul dans le r\u00e9pertoire Musique, combien de blocs utilise alors ce r\u00e9pertoire?"
    },
    {
        "guid": "da3590dc-4da0-4790-bd94-b9e56450702b",
        "model_answer": "Soit \\(I=]a,b[\\), \\(f:I\\to \\bR\\).\nVrai ou faux? Si \\(f\\in C^1(I)\\), alors \\(f\\) est continue sur \\(I\\). Si \\(f\\in C^1(I)\\), alors il n'existe aucun \\(x_0\\in I\\) o\u00f9 \\(f\\) est\ndeux fois d\u00e9rivable. Si \\(f^{(k)}\\) existe, alors \\(f\\in C^k(I)\\). Si \\(f\\in C^1(I)\\), alors \\(f':I\\to \\bR\\) est born\u00e9e. Si \\(f\\in C^1(I)\\), et si \\(f'\\) n'est pas born\u00e9e, alors \\(f\\) n'est\npas born\u00e9e.\n Si \\(f\\in C^k(I)\\), alors \\(f\\in C^j(I)\\) pour tout entier\n\\(1\\leq j\\lt k\\). Si \\(f\\in C^k(I)\\), alors pour tout \\(x_0\\in I\\) et tout \n\\(j\\in \\{1,2,\\dots,k\\}\\), \\(\\lim_{x\\to x_0}f^{(j)}(x)=f^{(j)}(x_0)\\). Si \\(f'(x)=|x|\\), alors \\(f\\in C^1(I)\\). Si \\(f'(x)=|x|\\), alors \\(f'(x)=f^{(j)}(x_0)\\). Si \\(f'(x)=|x|\\), alors \\(f'(x)=f^{(j)}(x_0)\\). Si \\(f'(x)=|x|\\), alors \\(f'(x)=f^{(j)}(x_0)\\). Si \\(f'(x)=|x|\\), alors \\(f'(x)=f^{(j)}(x_0)\\). Si \\(f'(x)=|x|\\), alors \\(f'(x)=f^{(j)}(x_0)\\). Si \\(f'(x)=|x|\\), alors \\(f'(x)=f^{(j)}(x_0)\\). Si \\(f'(x)=|x|\\), alors \\(f'(x)=f^{(j)}(x_0)\\). Si \\(f'(x)=|x|\\), alors \\(f'(x)=f^{(j)}(x_0)\\). Si \\(f'(x)=|x|\\), alors \\(f'(x)=f^{(j)}(x_0)\\). Si \\(f'(x)=|x|\\), alors \\(f'(x)=f"
    },
    {
        "guid": "299255b4-6b4b-423b-bafa-e1f2ca04ecb5",
        "model_answer": "When representing the adjacency list of a Web page in a connectivity server by using a reference list from another Web page, the reference list is searched only in a neighboring window of the Web page's URL, because: Subsequent URLs in an adjacency list have typically small differences Typically many URLs in a web page are similar to each other Often many URLs among two pages with similar URL are similar Most extra nodes are found in the neighboring window of the Web page's URL\n\nWhat is the correct way to represent the adjacency list of a Web page in a connectivity server by using a reference list from another Web page?\n\n[![enter image description here](https://i.stack.imgur.com/r0B4.png)](https://i.stack.imgur.com/r0B4.png)\n\n[![enter image description here](https://i.stack.imgur.com/r1Fz.png)](https://i.stack.imgur.com/r1Fz.png)\n\n[![enter image description here](https://i.stack.imgur.com/r2H3.png)](https://i.stack.imgur.com/r2H3.png)\n\n[![enter image description here](https://i.stack.imgur.com/r3Ft.png)](https://i.stack.imgur.com/r3Ft.png)\n\n[![enter image description here](https://i.stack.imgur.com/r4B7.png)](https://i.stack.imgur.com/r4B7.png)\n\n[![enter image description here](https://i.stack.imgur.com/r5B5.png)](https://i.stack.imgur.com"
    },
    {
        "guid": "92251192-94ec-4d07-a94c-34775db00d70",
        "model_answer": " Now let $\\xv$ be a random vector distributed according to the uniform distribution over the finite centered dataset $\\xv_1,..., \\xv_N$ from above. %\nConsider the problem of finding a unit vector, $\\wv \\in \\R^D$, such that the random variable $\\wv^\top \\xx$ has \\emph{maximal} variance. What is the variance of the random variable $\\wv^\top \\xx$ over the randomness of $\\xx$?\n\n[asy]\nunitsize(1 cm);\n\npair A,B,C,D,E,F,G,H,I,J,K,L,M,N,O,P,Q,R,S,T,U,V,W,X,Y,Z;\nA = (0,0);\nB = (0,1);\nC = (0,2);\nD = (0,3);\nE = (0,4);\nF = (0,5);\nG = (0,6);\nH = (0,7);\nI = (0,8);\nJ = (0,9);\nK = (0,10);\nL = (0,11);\nM = (0,12);\nN = (0,13);\nO = (0,14);\nP = (0,15);\nQ = (0,16);\nR = (0,17);\nS = (0,18);\nT = (0,19);\nU = (0,20);\nV = (0,21);\nW = (0,22);\nX = (0,23);\nY = (0,24);\nZ = (0,25);\n\ndraw(A--B--C--D--E--F--G--H--I--J--K"
    },
    {
        "guid": "b82db1db-a6f9-4e3a-8d45-9a89cfddd953",
        "model_answer": "You are using a 3-layer fully-connected neural, and you are using \\textbf{$f(x) = 2x$ as your activation function}. Your input data has components in [0, 1]. \\textbf{You initialize your weights using Kaiming (He) initialization}, and set all the bias terms to 0. You start optimizing using SGD. What will likely happen? The gradient is 0 so nothing happens The gradient is very large so the model can't converge Training is fine, but our neural net does only as well as a linear model Everything is fine, but the gradient is very large so the model can't converge The gradient is very large so the model can't converge"
    },
    {
        "guid": "e07a6c79-461a-40f2-b8a8-402f92e38839",
        "model_answer": "Wave plates are birefringent materials that change the polarization state of a beam depending on their thickness $(d)$. In these devices, the ordinary axis generates a phase of $e^{\\frac{2 \\pi}{\\lambda} d n_{x}}$ for $E_{x}$ field while the extraordinary axis generates $e^{\\frac{2 \\pi}{\\lambda} d n_{y}}$ phase difference for $E_{y}$ field $\\left(n_{x}, n_{x}\\right.$ are the refractive indexes). The phase difference for quarter wave plates (QWP) and for half wave plates (HWP) are $\\frac{\\pi}{2}$ and $\\pi$ respectively.\n\nFind the polarization state of a $\\alpha$-degree linearly polarized input beam that is passing through a HWP (use jones vector representation).\n\n[asy]\nimport tensorflow as tf;\n\nimport matplotlib.pyplot as plt;\n\nimport matplotlib.linalg;\n\nimport matplotlib.linalg.linalg2;\n\nimport matplotlib.linalg.linalg3;\n\nimport matplotlib.linalg.linalg4;\n\nimport matplotlib.linalg.linalg5;\n\nimport matplotlib.linalg.linalg6;\n\nimport matplotlib.linalg.linalg7;\n\nimport matplotlib.linalg.linalg8;\n\nimport matplotlib.linalg.linalg9;\n\nimport matplotlib.linalg.linalg10;\n\nimport matplotlib.linalg.linalg11;\n\nimport matplotlib.linalg.linalg12;\n\nimport matplotlib.linalg.linalg13;\n\nimport matplotlib.linalg.linalg14;\n\nimport matplotlib.linalg.linalg15;\n\nimport matplotlib.linalg.linalg16;\n\nimport matplotlib.linalg.linalg17;\n\nimport matplotlib."
    },
    {
        "guid": "1f0c9830-5cb9-44ef-865a-1681b7cae654",
        "model_answer": "Chaque \u00e9lectron poss\u00e8de un degr\u00e9 de libert\u00e9 quantique qui s'appelle le spin. Le spin est analogue \u00e0 un aimant microscopique avec un p\u00f4le nord et un p\u00f4le sud. \n     La composante du spin $\u000bec{S}$ de chaque \u00e9lectron selon un axe donn\u00e9 (par ex. $S_z$ selon $z$) ne peut prendre que 2 valeurs:\n     1. $S_z=+1$ (vers le haut) ou\n     2. $S_z=-1$ (vers le bas)\n     Lorsque plus de spins pointent dans une direction plut\u00f4t qu'une autre, le spin total (somme des spins individuels) est non nul et il existe une magn\u00e9tisation du mat\u00e9riau (c'est un aimant au sens commun du terme).\n     Nous voulons \u00e9tudier la physique statistique d'un ensemble de 50 \u00e9lectrons, ayant chacun leur spin pouvant pointer vers \n     le haut ou vers le bas. Cet exercice est particuli\u00e8rement int\u00e9ressant \u00e0 faire chez vous avec un ordinateur \n     (par exemple avec Python) ou une calculatrice graphique, pour les applications num\u00e9riques.\n     Combien existent-ils d'\u00e9tats microscopiques? \n     Il existe une magn\u00e9tisation du mat\u00e9riau (c'est un aimant au sens commun du terme) ou une calculatrice graphique, pour les applications num\u00e9riques.\n     Nous voulons \u00e9tudier la physique statistique d'un ensemble de 50 \u00e9lectrons, ayant chacun leur spin pouvant pointer vers \n     le haut ou vers le bas. Cet exercice est particuli\u00e8rement int\u00e9ressant \u00e0 faire chez vous avec un ordinateur \n     (par exemple avec Python) ou une calculatrice graphique, pour les applications num\u00e9riques.\n     Nous voulons \u00e9tudier la physique statistique d'un ensemble de 50 \u00e9lectrons, ayant chacun leur spin pouvant pointer vers \n     le haut ou vers le bas. Cet exercice est particuli\u00e8rement int\u00e9ressant \u00e0 faire chez vous avec un ordinateur \n     (par exemple avec Python) ou une calculatrice graphique, pour les applications num\u00e9riques.\n     Nous voulons \u00e9tudier la physique statistique d'un ensemble de 50 \u00e9lect"
    },
    {
        "guid": "8dca0280-913e-469b-a9b0-e0edea7fc589",
        "model_answer": "What value would be stored by the Viterbi algorithm in the node associated to V for the word \"time\"?\n\n[asy]\nunitsize(0.5 cm);\n\npair A, B, C, D, E, F, G, H, I, J, K, L, M, N, O, P, Q, R, S, T, U, V, W, X, Y, Z;\n\nA = (0,0);\nB = (0,1);\nC = (0,2);\nD = (0,3);\nE = (0,4);\nF = (0,5);\nG = (0,6);\nH = (0,7);\nI = (0,8);\nJ = (0,9);\nK = (0,10);\nL = (0,11);\nM = (0,12);\nN = (0,13);\nO = (0,14);\nP = (0,15);\nQ = (0,16);\nR = (0,17);\nS = (0,18);\nT = (0,19);\nU = (0,20);\nV = (0,21);\nW = (0,22);\nX = (0,23);\nY = (0,24);\nZ = (0,25);\n\ndraw(A--B--C--D--E--F--G--H--I--"
    },
    {
        "guid": "e82b5b83-63be-4052-8b90-856964aa898b",
        "model_answer": "Soit \\(f\\colon [a,b]\\to\\mathbb{R}\\) une fonction continue, \nd\u00e9rivable sur \\(]a,b[\\).\nVrai ou faux?\n\\begin{enumerate}\n\\item Si \\(f'(x)\\geq 0\\) pour tout \\(x\\in\\:]a,b[\\,\\), alors \\(f\\) est croissante sur\n\\([a,b]\\).\n\\item Si \\(f\\) est croissante sur \\([a,b]\\), alors \\(f'(x)\\geq 0\\) pour tout\n\\(x\\in\\:]a,b[\\,\\).\n\\item Si \\(f\\) est strictement croissante sur \\([a,b]\\), alors \\(f'(x)> 0\\) pour tout\n\\(x\\in\\:]a,b[\\,\\).\n\\item Si \\(f'(x)> 0\\) pour tout \\(x\\in\\:]a,b[\\,\\), alors \\(f\\) est strictement\ncroissante sur \\([a,b]\\).\n\\item Si \\(\\lim\\limits_{x\\to a^+}f'(x)=\\ell\\) existe, alors \\(f\\) est d\u00e9rivable \u00e0\ndroite en \\(a\\) et la d\u00e9riv\u00e9e \u00e0 droite est \\(f'_+(a)=\\ell\\).\n\\end{enumerate}\n\nPour tout \\(x\\in\\:]a,b[\\,\\), alors \\(f'(x)\\geq 0\\) pour tout \\(x\\in\\:]a,b[\\,\\), alors \\(f'(x)\\geq 0\\) pour tout \\(x\\in\\:]a,b[\\,\\), alors \\(f'(x)\\geq 0\\) pour tout \\(x\\in\\:]a,b[\\,\\), alors \\(f'(x)\\geq 0\\) pour tout \\(x\\in\\:]a,b[\\,\\), alors \\(f'(x)\\geq 0\\) pour tout \\(x\\in\\:]a,b[\\,\\), alors \\(f'(x)\\geq 0\\) pour tout \\(x\\in\\:]a,b[\\,\\), alors \\(f'(x)\\geq 0\\) pour tout \\(x\\in\\:]a,b[\\,\\), alors \\(f'(x)\\geq 0\\) pour tout \\(x\\in\\:]a,b[\\,\\), alors \\(f'(x)\\geq 0\\) pour tout \\(x\\in\\:]a,b[\\,\\), alors \\(f'(x)\\geq 0\\) pour tout \\(x\\in"
    },
    {
        "guid": "fb202e2b-e599-44d7-b4ff-3fec50e91311",
        "model_answer": "What is the mean squared error of $f$ for a sample, where $\\textbf{x}$ is an input, $y$ a target and $f(\\textbf{x},W)$ the mapping function ? \n\t(One answer)  $||y - f(\\textbf{x},W)||^2 $   $||y - f(\\textbf{x},W)|| $  $-\\log(P(y=i | \\textbf{x})) = -\\log(\\frac{e^{\\textbf{f}_i(\\textbf{x},W)}}{\\sum_j e^{\\textbf{f}_j(\\textbf{x},W)}})$   $P(y=i |\\textbf{x}) = \\frac{e^{\\textbf{f}_i(\\textbf{x},W)}}{\\sum_j e^{\\textbf{f}_j(\\textbf{x},W)}}$                                                                                                                                                                                                                                                                                                             "
    },
    {
        "guid": "7690f1a8-df38-4e65-a667-09f0877fb255",
        "model_answer": "With respect to reorder buffers, Would you expect to find the memory address where a particular\n  instruction was fetched (i.e., the value of the PC at the time of fetching) inside the reorder buffer? If so, why would it be there? If not, elaborate on why it would it be unneeded.\n\nFor example, if I have a buffer that holds a pointer to a pointer to a buffer that holds a pointer to a buffer that holds a pointer to a buffer that holds a pointer to a buffer that holds a pointer to a buffer that holds a pointer to a buffer that holds a pointer to a buffer that holds a pointer to a buffer that holds a pointer to a buffer that holds a pointer to a buffer that holds a pointer to a buffer that holds a pointer to a buffer that holds a pointer to a buffer that holds a pointer to a buffer that holds a pointer to a buffer that holds a pointer to a buffer that holds a pointer to a buffer that holds a pointer to a buffer that holds a pointer to a buffer that holds a pointer to a buffer that holds a pointer to a buffer that holds a pointer to a buffer that holds a pointer to a buffer that holds a pointer to a buffer that holds a pointer to a buffer that holds a pointer to a buffer that holds a pointer to a buffer that holds a pointer to a buffer that holds a pointer to a buffer that holds a pointer to a buffer that holds a pointer to a buffer that holds a pointer to a buffer that holds a pointer to a buffer that holds a pointer to a buffer that holds a pointer to a buffer that holds a pointer to a buffer that holds a pointer to a buffer that holds a pointer to a buffer that holds a pointer to a buffer that holds a pointer to a buffer that holds a pointer to a buffer"
    },
    {
        "guid": "a442d457-38a3-4ec4-898f-89cbbf5db372",
        "model_answer": "Montrer que\n\\[ \\sum_{n\\geq 3} \\frac{1}{n(\\ln(n))^\\mu}\n\\begin{cases}\n\\text{converge}&\\text{ si }\\mu>1\\,,\\\\\n\\text{diverge}&\\text{ si }\\mu\\leq 1\\,.\n\\end{cases}\n\\]Find\n\\[\\sum_{n\\geq 3} \\frac{1}{n(\\ln(n))^\\mu} + \\sum_{n\\geq 3} \\frac{1}{n(\\ln(n))^\\mu} + \\sum_{n\\geq 3} \\frac{1}{n(\\ln(n))^\\mu} + \\sum_{n\\geq 3} \\frac{1}{n(\\ln(n))^\\mu} + \\sum_{n\\geq 3} \\frac{1}{n(\\ln(n))^\\mu} + \\sum_{n\\geq 3} \\frac{1}{n(\\ln(n))^\\mu} + \\sum_{n\\geq 3} \\frac{1}{n(\\ln(n))^\\mu} + \\sum_{n\\geq 3} \\frac{1}{n(\\ln(n))^\\mu} + \\sum_{n\\geq 3} \\frac{1}{n(\\ln(n))^\\mu} + \\sum_{n\\geq 3} \\frac{1}{n(\\ln(n))^\\mu} + \\sum_{n\\geq 3} \\frac{1}{n(\\ln(n))^\\mu} + \\sum_{n\\geq 3} \\frac{1}{n(\\ln(n))^"
    },
    {
        "guid": "bfb2e9ae-9035-40ee-8406-b95519d675ac",
        "model_answer": "L\u2019acc\u00e9l\u00e9rateur de particules LHC du CERN g\u00e9n\u00e8re 1 Po/s (= 10^(15) octets/s), soit l\u2019\u00e9quivalent de 12 ans de vid\u00e9o en HD par seconde! Il n\u2019y a simplement aucune technologie au monde qui puisse enregistrer toutes ces donn\u00e9es en temps r\u00e9el. M\u00eame en mettant beaucoup de disques en parall\u00e8le, on n\u2019arriverait pas \u00e0 construire une connexion assez rapide pour y enregistrer toutes ces donn\u00e9es en temps r\u00e9el sans en perdre.\nUne batterie de circuits logiques (hardware) analysent ces donn\u00e9es en temps r\u00e9el et les filtrent par un facteur de l\u2019ordre de 1000 avant de les injecter directement dans les m\u00e9moires centrales d\u2019une batterie de processeurs sp\u00e9cialis\u00e9s qui les r\u00e9duisent encore par un facteur de l\u2019ordre de 1000.\nEn arrondissant aux ordres de grandeur, combien de disques \u00e0 100 Mo/s en parall\u00e8le sont n\u00e9cessaires pour un d\u00e9bit de 1 Go/s?\nCette \u00e9quation est n\u00e9cessaire pour un d\u00e9bit de 1 Go/s, on peut \u00eatre utilis\u00e9 pour un d\u00e9bit de 1 Go/s, on peut \u00eatre utilis\u00e9 pour un d\u00e9bit de 1 Go/s, on peut \u00eatre utilis\u00e9 pour un d\u00e9bit de 1 Go/s, on peut \u00eatre utilis\u00e9 pour un d\u00e9bit de 1 Go/s, on peut \u00eatre utilis\u00e9 pour un d\u00e9bit de 1 Go/s, on peut \u00eatre utilis\u00e9 pour un d\u00e9bit de 1 Go/s, on peut \u00eatre utilis\u00e9 pour un d\u00e9bit de 1 Go/s, on peut \u00eatre utilis\u00e9 pour un d\u00e9bit de 1 Go/s, on peut \u00eatre utilis\u00e9 pour un d\u00e9bit de 1 Go/s, on peut \u00eatre utilis\u00e9 pour un d\u00e9bit de 1 Go/s, on peut \u00eatre utilis\u00e9 pour un d\u00e9bit de 1 Go/s, on peut \u00eatre utilis\u00e9 pour un d\u00e9bit de 1 Go/s, on peut \u00eatre utilis\u00e9 pour un d\u00e9bit de 1 Go/s, on peut \u00eatre utilis\u00e9 pour un d\u00e9bit de 1 Go/s, on peut \u00eatre utilis\u00e9 pour un d\u00e9bit"
    },
    {
        "guid": "6fab6a7c-f678-401b-965d-4b1b7e514852",
        "model_answer": "What is the worst case complexity of listing the contents of the directory? The file system implements directories as linked-lists. $O(1)$ $O(number of direntries in the directory)$ $O(size of the file system)$ $O(number of direntries in the file system)$ $O(log(number of direntries in the directory))$ $O(log(number of direntries in the file system))$ $O(log(number of direntries in the file system))$ $O(log(number of direntries in the file system))$ $O(log(number of direntries in the file system))$ $O(log(number of direntries in the file system))$ $O(log(number of direntries in the file system))$ $O(log(number of direntries in the file system))$ $O(log(number of direntries in the file system))$ $O(log(number of direntries in the file system))$ $O(log(number of direntries in the file system))$ $O(log(number of direntries in the file system))$ $O(log(number of direntries in the file system))$ $O(log(number of direntries in the file system))$ $O(log(number of direntries in the file system))$ $O(log(number of direntries in the file system))$ $O(log(number of direntries in the file system))$ $O(log(number of direntries in the file system))$ $O(log(number of direntries in the file system))$ $O(log(number of direntries in the"
    },
    {
        "guid": "841d52c7-5353-424c-a1f4-8ebf473ecc6d",
        "model_answer": "Let $f(\\mathbf{x})=\\frac{1}{n} \\sum_{i=1}^n f_i(\\mathbf{x})$ where the functions $f_i(\\mathbf{x})$ are $L$-smooth and convex. Again, consider the optimization problem: $$ \\min _{\\mathbf{x} \\in \\mathbb{R}^p} f(\\mathbf{x}) $$ We want to solve the problem using the minibatch Stochastic Gradient Descent (SGD). Write and explain the update rule for SGD with a batch size $B$ and a constant step-size $\\alpha=\\frac{1}{L}$.\n\n[asy]\nunitsize(1 cm);\n\npair A,B,C,D,E,F,G,H,I,J,K,L,M,N,O,P,Q,R,S,T,U,V,W,X,Y,Z;\n\nA = (0,0);\nB = (0,1);\nC = (0,2);\nD = (0,3);\nE = (0,4);\nF = (0,5);\nG = (0,6);\nH = (0,7);\nI = (0,8);\nJ = (0,9);\nK = (0,10);\nL = (0,11);\nM = (0,12);\nN = (0,13);\nO = (0,14);\nP = (0,15);\nQ = (0,16);\nR = (0,17);\nS = (0,18);\nT = (0,19);\nU = (0,20);\nV = (0,21);\nW = (0,22);\nX = (0,23);\nY = (0,24);\nZ = (0,25);\ndraw(A--B--C--D--E--F--G--H--I--J--K"
    },
    {
        "guid": "f72cf01b-8f66-4e8f-a3b9-3bfb27f562d7",
        "model_answer": "Consider a linear model $\\hat{y} = xv ^\top \\wv$ with the squared loss under an $\\ell_\\infty$-bounded adversarial perturbation. For a single point $(xv, y)$, it corresponds to the following objective:\n                    \begin{align}\n                        \\max_{\tilde{xv}:\\ \\|xv-\tilde{xv}\\|_\\infty\\leq \\epsilon} \\left(y - \tilde{xv} ^\top \\wv \right)^{2},\n                        \tag{OP}\\AMClabel{eq:opt_adv_regression}\n                    \\end{align}\n                    where $\\|xv-\tilde{xv}\\|_\\infty\\leq \\epsilon$ denotes the $\\ell_\\infty$-norm, i.e.  $|x_i - \tilde{x}_i| \\leq \u000barepsilon$ for every $i$.\n                    \\\n                    Assume that $\\wv = (3, -2)^\top$, $xv = (-1, 2)^\top$, $y=2$. What is the maximum value of the optimization problem in Eq.~(\\AMCref{eq:opt_adv_regression})?\n\t                 $(5+9\u000barepsilon)^2$ $(3+10\u000barepsilon)^2$ $(10-\u000barepsilon)^2$ Other $(9+5\u000barepsilon)^2$\n                                                                                                                                                                                                                                                                                                           "
    },
    {
        "guid": "60c20157-95f6-4cf5-b71c-29ce9d194200",
        "model_answer": "Write a function that takes as input the data matrix X and the labels y, and returns the coefficient and the bias of linear regression predictor \n            using the closed-form solution.\n                                                                                                                                                                                                                                                                                                           "
    },
    {
        "guid": "3538e748-434d-4ed8-adc3-e9bda94c46c9",
        "model_answer": "Vrai ou faux? Si \\(a_n\\leq b_n\\) pour tout \\(n\\geq 1\\), et si \\(\\sum_{n\\geq 1}b_n\\) converge,\nalors \\(\\sum_{n\\geq 1}a_n\\) converge aussi.\n Si il existe deux sous-suites \\((a_{n_k})_k\\) et \\((b_{n_k})_k\\)\ntelles que \\(0\\leq a_{n_k}\\leq b_{n_k}\\) pour tout \\(k\\) suffisamment grand,\net si \\(\\sum_nb_{n}\\) converge, alors \\(\\sum_na_{n}\\) converge aussi.\n Si il existe deux sous-suites \\((a_{n_k})_k\\) et \\((b_{n_k})_k\\)\ntelles que \\(0\\leq a_{n_k}\\leq b_{n_k}\\) pour tout \\(k\\) suffisamment grand,\net si \\(\\sum_kb_{n_k}\\) converge, alors \\(\\sum_ka_{n_k}\\) converge aussi.\nSi \\(a_n\\leq b_n\\) pour tout \\(n\\geq 1\\), et si \\(\\sum_{n\\geq 1}a_n\\) converge,\nalors \\(\\sum_{n\\geq 1}b_n\\) converge aussi.\nSi \\(a_n\\leq b_n\\) pour tout \\(n\\geq 1\\), et si \\(\\sum_{n\\geq 1}a_n\\) converge,\nalors \\(\\sum_{n\\geq 1}b_n\\) converge aussi.\nSi \\(a_n\\leq b_n\\) pour tout \\(n\\geq 1\\), et si \\(\\sum_{n\\geq 1}a_n\\) converge,\nalors \\(\\sum_{n\\geq 1}b_n\\) converge aussi.\nSi \\(a_n\\leq b_n\\) pour tout \\(n\\geq 1\\), et si \\(\\sum_{n\\geq 1}a_n\\) converge,\nalors \\(\\sum_{n\\geq 1}b_n\\) converge aussi.\nSi \\(a_n\\leq b_n\\) pour tout \\(n\\geq 1\\), et si \\(\\sum_{n\\geq 1}a_n\\) converge,\nalors \\(\\sum_{n\\geq 1}"
    },
    {
        "guid": "426d5d69-1a8d-4aca-b6f3-71b5a9af11ab",
        "model_answer": "A leftist min heap is a tree that satisfies the following properties:\nP.1 Min heap: For any given node C, if P is a parent node of C, then the value of P is less than or equal\nto the value of C.\nP.2 Leftist heap: For any given node C, if L is a left child of C and R is a right child of C, then the rank\nof R is less than or equal to the rank of L. Here, rank of C is the number of edges on the shortest path\nfrom node C to a leaf node.\nConsider the following implementation of a leftist min heap:\n1 sealed abstract class Heap\n2 case class Empty() extends Heap\n3 case class Node(rank: Int, value: Int, h1: Heap, h2: Heap) extends Heap\n4 def rank(h: Heap): Int = h match\n5 case Empty() => -1\n6 case Node(r, v, h1, h2) => r\n7 def insert(x: Int, h: Heap) = merge(h, Node(0, x, Empty(), Empty()))\n8 def findMin(h: Heap): Int = h match\n9 case Empty() => 0\n10 case Node(_, x, _, _) => x\n11 def deleteMin(h: Heap): Heap = h match\n12 case Empty() => h\n13 case Node(_, x, lh, rh) => merge(lh, rh)\n14\n15 // Merge two leftist min heaps h1 and h2\n16 def merge(h1: Heap, h2: Heap): Heap =\n17 def shake(x: Int, lh: Heap, rh: Heap) =\n18 // Ensure the leftist property\n19 (lh, rh) match\n20 SSS\n21 case _ => Node(rank(lh) + 1, x, rh, lh)\n22 // Ensure the min property\n23 (h1, h2) match\n24 case (Empty(), h) => h\n25 case (h, Empty()) => h\n26 MMM\n27 case (Node(_, x1, lh1, rh1), _: Node) => shake(x1, lh1, merge(h1, rh1))\n28 case (Node(_, x2, lh2, rh2), _: Node) => shake(x2, lh2, merge(h2, rh2))\n29 case (Node(_, x3, lh3, rh3), _: Node) => shake(x3, lh3, merge(h3, rh3))\n30 case (Node(_, x4, lh4, rh4), _: Node) => shake(x4, lh4, merge(h4, rh4))\n31 case (Node(_, x5, lh5, rh5), _: Node) => shake(x5, lh5, merge(h5, rh5))\n32 case (Node(_, x6, lh6, rh6), _: Node) => shake(x6, lh6, merge(h6, rh6))\n33 case (Node(_, x7, lh7, rh7), _: Node) => shake(x7, lh7, merge(h7, rh7))\n34 case (Node(_, x8, lh8, rh8), _: Node) => shake(x8, lh8, merge(h8, rh8))\n35 case (Node(_, x9, lh9, rh9), _: Node"
    },
    {
        "guid": "30afbb49-8450-43c9-bb4d-ffd127127497",
        "model_answer": "Determine the logarithmic negativity of the state  \\(\\dfrac{1}{\\sqrt{3}}|\\uparrow\\rangle_A|\\uparrow\\rangle_B - \\sqrt{\\dfrac{2}{3}}|\\downarrow\\rangle_A|\\downarrow\\rangle_B\\) \\(\\log\\big(3+\\sqrt{2}\\big)\\) \\(\\log\\big(1+\\dfrac{2}{3}\\sqrt{2}\\big)\\) \\(\\log\\big(1+\\sqrt{3}\\big)\\) \\(\\log\\big(1+\\sqrt{3}\\big)\\) \\(\\log\\big(1+\\sqrt{3}\\big)\\) \\(\\log\\big(1+\\sqrt{3}\\big)\\) \\(\\log\\big(1+\\sqrt{3}\\big)\\) \\(\\log\\big(1+\\sqrt{3}\\big)\\) \\(\\log\\big(1+\\sqrt{3}\\big)\\) \\(\\log\\big(1+\\sqrt{3}\\big)\\) \\(\\log\\big(1+\\sqrt{3}\\big)\\) \\(\\log\\big(1+\\sqrt{3}\\big)\\) \\(\\log\\big(1+\\sqrt{3}\\big)\\) \\(\\log\\big(1+\\sqrt{3}\\big)\\) \\(\\log\\big(1+\\sqrt{3}\\big)\\) \\(\\log\\big(1+\\sqrt{3}\\big)\\) \\(\\log\\big(1+\\sqrt{3}\\big)\\) \\(\\log\\big(1+\\sqrt{3}\\big)\\) \\(\\log\\big(1+\\sqrt{3}\\big)\\) \\(\\log\\big(1+\\sqrt{3}\\big)\\) \\(\\log\\big(1+\\sqrt{3}\\big)\\) \\(\\log\\big(1+\\sqrt{3"
    },
    {
        "guid": "7c17680c-400d-4adf-96cb-7af4b14ff562",
        "model_answer": "Calculer l'int\u00e9grale\n\\(\n\\int_{0}^{\\pi^{1/33}}\\sin(\\sin(x^{33}))\\,\\cos(x^{33})\\,x^{32}\\,dx\\:.\n\\)\n\\begin{align*}\n\\int_{0}^{\\pi^{1/33}}\\sin(\\sin(x^{33}))\\,\\cos(x^{33})\\,x^{32}\\,dx\\:.\n\\end{align*}\n\\begin{align*}\n\\int_{0}^{\\pi^{1/33}}\\sin(\\sin(x^{33}))\\,\\cos(x^{33})\\,x^{32}\\,dx\\:.\n\\end{align*}\n\\begin{align*}\n\\int_{0}^{\\pi^{1/33}}\\sin(\\sin(x^{33}))\\,\\cos(x^{33})\\,x^{32}\\,dx\\:.\n\\end{align*}\n\\begin{align*}\n\\int_{0}^{\\pi^{1/33}}\\sin(\\sin(x^{33}))\\,\\cos(x^{33})\\,x^{32}\\,dx\\:.\n\\end{align*}\n\\begin{align*}\n\\int_{0}^{\\pi^{1/33}}\\sin(\\sin(x^{33}))\\,\\cos(x^{33})\\,x^{32}\\,dx\\:.\n\\end{align*}\n\\begin{align*}\n\\int"
    },
    {
        "guid": "d9b30a74-5f67-4c4a-9a83-e9bfd09bc47d",
        "model_answer": "Si \\(A\\subset \\bR\\) n'est pas ouvert, alors il est ferm\u00e9. son compl\u00e9mentaire est ouvert. il existe au moins un \\(x\\in A\\) tel que\n\\(]x-\\epsilon,x+\\epsilon[\\not\\subset A\\) pour tout \\(\\epsilon>0\\). pour tout \\(x\\in A\\), il n'existe aucun \\(\\epsilon>0\\) tel que\n\\(]x-\\epsilon,x+\\epsilon[\\subset A\\). son compl\u00e9mentaire n'est pas ouvert non plus.\n\nSi \\(A\\subset \\bR\\) n'est pas ouvert, alors il est ferm\u00e9. son compl\u00e9mentaire est ouvert. il existe au moins un \\(x\\in A\\) tel que\n\\(]x-\\epsilon,x+\\epsilon[\\not\\subset A\\) pour tout \\(\\epsilon>0\\). pour tout \\(x\\in A\\), il n'existe aucun \\(\\epsilon>0\\) tel que\n\\(]x-\\epsilon,x+\\epsilon[\\subset A\\). son compl\u00e9mentaire n'est pas ouvert non plus.\n\nSi \\(A\\subset \\bR\\) n'est pas ouvert, alors il est ferm\u00e9. son compl\u00e9mentaire est ouvert. il existe au moins un \\(x\\in A\\) tel que\n\\(]x-\\epsilon,x+\\epsilon[\\not\\subset A\\) pour tout \\(\\epsilon>0\\). pour tout \\(x\\in A\\), il n'existe aucun \\(\\epsilon>0\\) tel que\n\\(]x-\\epsilon,x+\\epsilon[\\subset A\\). son compl\u00e9mentaire"
    },
    {
        "guid": "99de7be3-24e6-45b7-9ef3-a9f1bd649c8a",
        "model_answer": "Wave plates are birefringent materials that change the polarization state of a beam depending on their thickness $(d)$. In these devices, the ordinary axis generates a phase of $e^{\\frac{2 \\pi}{\\lambda} d n_{x}}$ for $E_{x}$ field while the extraordinary axis generates $e^{\\frac{2 \\pi}{\\lambda} d n_{y}}$ phase difference for $E_{y}$ field $\\left(n_{x}, n_{x}\\right.$ are the refractive indexes). The phase difference for quarter wave plates (QWP) and for half wave plates (HWP) are $\\frac{\\pi}{2}$ and $\\pi$ respectively.\n\nAssume a $\\frac{\\pi}{4}$ degree polarized input beam and find the jones vector representation of the output beam if it is passing through a QWP/HWP.\n\n[asy]\nsize(150);\n\npair A,B,C,D,E,F,G,H,I,J,K,L,M,N,O,P,Q,R,S,T,U,V,W,X,Y,Z,A,B,C,D,E,F,G,H,I,J,K,L,M,N,O,P,Q,R,S,T,U,V,W,X,Y,Z,A,B,C,D,E,F,G,H,I,J,K,L,M,N,O,P,Q,R,S,T,U,V,W,X,Y,Z,A,B,C,D,E,F,G,H,I,J,K,L,M,N,O,P,Q,R,S,T,U,V,W,X,Y,Z,A,B,C,D,E,F,G,H,I,J,K,L,M,N,O,P,Q,R,S,T,U,V,W,X,Y,Z,A,B,C,D,E,F,G,H,I,J,K,L,M,N"
    },
    {
        "guid": "f2ccb67e-6051-4111-8434-0209cad56ee3",
        "model_answer": "Many general evaluation metrics can be considered for various NLP tasks. The simplest one is accuracy. Give several examples of NLP tasks for which accuracy can be used as an evaluation metric. Justify why. In general, what property(ies) must an NLP task satisfy in order to be evaluable through accuracy?\n\n[asy]\nunitsize(0.8 cm);\n\npair A,B,C,D,E,F,G,H,I,J,K,L,M,N,O,P,Q,R,S,T,U,V,W,X,Y,Z;\n\nA = (0,0);\nB = (1,0);\nC = (2,0);\nD = (3,0);\nE = (4,0);\nF = (5,0);\nG = (6,0);\nH = (7,0);\nI = (8,0);\nJ = (9,0);\nK = (10,0);\nL = (11,0);\nM = (12,0);\nN = (13,0);\nO = (14,0);\nP = (15,0);\nQ = (16,0);\nR = (17,0);\nS = (18,0);\nT = (19,0);\nU = (20,0);\nV = (21,0);\nW = (22,0);\nX = (23,0);\nY = (24,0);\nZ = (25,0);\n\ndraw(A--B--C--D--E--F--G--H--I--"
    },
    {
        "guid": "04ca849b-3186-4abc-b865-c512d9119e0a",
        "model_answer": " List two common types of exceptions which must be implemented\n  precisely. Explain why. \n\n[![enter image description here](https://i.stack.imgur.com/k0qh.jpg)](https://i.stack.imgur.com/k0qh.jpg)\n\n[![enter image description here](https://i.stack.imgur.com/m4wj.jpg)](https://i.stack.imgur.com/m4wj.jpg)\n\n[![enter image description here](https://i.stack.imgur.com/k1qz.jpg)](https://i.stack.imgur.com/k1qz.jpg)\n\n[![enter image description here](https://i.stack.imgur.com/j5jq.jpg)](https://i.stack.imgur.com/j5jq.jpg)\n\n[![enter image description here](https://i.stack.imgur.com/l2j6.jpg)](https://i.stack.imgur.com/l2j6.jpg)\n\n[![enter image description here](https://i.stack.imgur.com/m5e4.jpg)](https://i.stack.imgur.com/m5e4.jpg)\n\n[![enter image description here](https://i.stack.imgur.com/l2f4.jpg)](https://"
    },
    {
        "guid": "36d8f75e-6249-4cab-9e1e-69571358b0ad",
        "model_answer": " In this exercise, you will craft a convolutional neural network f that detects edges in1D inputs. \n          Let the inputs be x \\in \\{0,1\\}^d of the form  x_k =(\\underbrace{1, 1, \\ldots, 1}_{k  times }, 0, \\ldots, 0), k \\in {0, \\ldots, d}, k \\in {0, \\ldots, d}.\n          For this input we say that the edge (i.e. where we switch from 1 to 0) is at position k. \n          The complete CNN will take x_k as input and output f(x_k)=k.\n          Build a convolutional layer A:\\{0,1\\}^{d+2} \\mapsto\\{0,1\\}^{d+1} such that A(\tilde{x}_k)_l=\\delta_{k l}, in other words \n          the only nonzero output should correspond to the position of the edge. \tilde{x} here is a padded version of x: \n          specify how to make the padding. To build $A$ use a single filter of size 2, a=(a_1, a_2). \n                                                                                                                                                                                                                                                                                                           "
    },
    {
        "guid": "e1a1b845-bc57-4250-a715-6b7bf2f3e192",
        "model_answer": "What is the edge betweenness for edge (7-5) in the following graph? 12.5 13 7.5 16.5 18.5 20.5 22.5 24.5 26.5 28.5 30.5 32.5 34.5 36.5 38.5 40.5 42.5 44.5 46.5 48.5 50.5 52.5 54.5 56.5 58.5 60.5 62.5 64.5 65.5 66.5 67.5 68.5 69.5 70.5 71.5 72.5 73.5 74.5 75.5 76.5 77.5 78.5 79.5 80.5 81.5 82.5 83.5 84.5 85.5 86.5 87.5 88.5 89.5 90.5 91.5 92.5 93.5 94.5 95.5 96.5 97.5 98.5 99.5 100.5 101.5 102.5 103.5 104.5 105.5 106.5 107.5 108.5 109.5 110.5 111.5 112.5 113.5 114.5 115.5 116.5 117.5 118.5 119.5 120.5 121.5 122.5 123.5 124.5 125.5 126.5 127.5 128.5 129.5 130.5 131.5 132.5 133.5 134.5 135.5 136.5 137.5 138.5 139.5 140"
    },
    {
        "guid": "7a2855e0-5c47-4622-b025-4dfa11353f41",
        "model_answer": "Concatenating two conc-trees of heights $h_1$ and $h_2$ yields a conc-tree with\nheight $h$ where $h_1$ and $h_2$ are concatenated.  What is the value of\n\\[\\frac{h_1}{h_2} + \\frac{h_2}{h_1} + \\frac{h_1}{h_2} + \\frac{h_2}{h_1} + \\frac{h_2}{h_2} + \\frac{h_1}{h_2} + \\frac{h_2}{h_1} + \\frac{h_2}{h_2} + \\frac{h_1}{h_2} + \\frac{h_2}{h_1} + \\frac{h_2}{h_2} + \\frac{h_1}{h_2} + \\frac{h_2}{h_1} + \\frac{h_2}{h_2} + \\frac{h_1}{h_2} + \\frac{h_2}{h_1} + \\frac{h_2}{h_2} + \\frac{h_1}{h_2} + \\frac{h_2}{h_1} + \\frac{h_2}{h_2} + \\frac{h_1}{h_2} + \\frac{h_2}{h_1} + \\frac{h_2}{h_2}"
    },
    {
        "guid": "f24af540-a417-4810-b572-c6a816fd36d8",
        "model_answer": "Last year Professor Ueli von Gruy\\`{e}res worked hard to to obtain an estimator $\\Alg$  to estimate the total cheese consumption of fondue lovers in Switzerland. For a small $\\epsilon >0$, his estimator \\Alg only  asks $3/\\epsilon^2$ random persons and have the following guarantee: if we  let $W$ denote the true answer and let $X$ be the random output of \\Alg then \\begin{align*} \\Pr[|X - W| \\geq \\epsilon W] \\leq 1/3\\,. %\\qquad \\mbox{ where $\\epsilon > 0$ is a small constant.} \\end{align*} However, Ueli is now stuck because the error probability of $1/3$ is too high.  We are  therefore going to help Ueli by designing a new estimator with a much higher success probability while still only asking relatively few persons. For a fixed small parameter $\\delta >0$, your task is to design and analyze an estimator that outputs a random value $Y$ with the following guarantee: \\begin{align} \\label{eq:guarantee2} \\Pr[|Y - W| \\geq \\epsilon W] \\leq \\delta\\,. %\\qquad \\mbox{ where $\\epsilon > 0$ is a small constant.} \\end{align} Your estimator should ask at most $3000\\log(1/\\delta)/\\epsilon^2$ persons about their preferences.  \\\\ While you should explain why your estimator works and what tools to use to analyze it, \\emph{you do not need to do any detailed calculations.} \\\\ {\\em (In this problem you are asked to (i) design an estimator that asks  at most $3000 \\log(1/\\delta)/\\epsilon^2$ persons  and (ii) explain why it satisfies the guarantee~\\eqref{eq:guarantee2}. Recall that you are allowed to refer to material covered in the lecture notes.)}\n\n[asy]\nunitsize(0.8 cm);\n\npair A,B,C,D,E,F,G,H,I,J,K,L,M,N,O,P,Q,R,S,T,U,V,W,X,Y,Z;\n\nA = (0,0);\nB = (0,1);\nC = (0,2);\nD = (0,3);\nE = (0,4);\nF = (0,5);\nG = (0,6);\nH = (0,7);\nI = (0,8);\nJ = (0,9);\nK = (0,10);\nL = (0,11);\nM = (0,12);\nN = (0,13);\nO = (0,14);\nP = (0,15);\nQ = (0,16);\nR = (0,17);\nS = (0,18);\nT = (0,19);\nU = (0,20);\nV = (0,21);\nW = (0,22);\nX = (0,23);\nY = (0,24);\nZ = (0,25);\ndraw(A--B--C--D--E--F--G--H--I--J"
    },
    {
        "guid": "aac16eb3-0584-4b0d-bee5-311565c0b0d7",
        "model_answer": "Soit \\(a_n\\to+\\infty\\).\nParmi les affirmations suivantes, lesquelles sont toujours vraies? Si \\(a_n\\leq b_n\\) pour une infinit\u00e9 d'indices \\(n\\), alors\n\\(b_n\\to\\infty\\).\n Si \\(a_n\\leq b_n\\) pour tout \\(n\\), alors \\(\\frac{1}{b_n}\\to 0\\). Si \\(b_n\\leq a_n\\), alors \\((b_n)\\) est major\u00e9e. Si \\(b_n\\) est minor\u00e9e, alors \\(a_nb_n\\to \\infty\\). Si il existe \\(\\delta\\geq 0\\) tel que \\(b_n\\geq \\delta\\) pour tout\n\\(n\\) suffisamment grand, alors \\(a_nb_n\\to \\infty\\). \n Si \\(r>1\\), alors \\(\\frac{a_n}{r^n}\\to 0\\). \\(e^{-a_n}\\to 0\\) \\(\\frac{\\sin(a_n)}{a_n}\\to 1\\) \\(\\frac{\\cos(a_n)}{a_n}\\to 0\\) \\(\\frac{\\sin(a_n)}{a_n}\\to 1\\) \\(\\frac{\\cos(a_n)}{a_n}\\to 0\\) \\(\\frac{\\sin(a_n)}{a_n}\\to 1\\) \\(\\frac{\\cos(a_n)}{a_n}\\to 0\\) \\(\\frac{\\sin(a_n)}{a_n}\\to 1\\) \\(\\frac{\\cos(a_n)}{a_n}\\to 0\\) \\(\\frac{\\sin(a_n)}{a_n}\\to 1\\) \\(\\frac{\\cos(a_n)}{a_n}\\to 0\\) \\(\\frac{\\sin(a_n)}{a_n}\\to 1\\) \\(\\frac{\\cos(a_n)}{a_n}\\to 0\\) \\(\\frac{\\sin(a_n)}{a_n}\\to 1\\) \\(\\frac{\\cos(a_n)}{a_n}\\to 0\\) \\(\\frac{\\sin(a_n)}{a_n}\\to 1\\) \\(\\frac{\\cos(a_n)}{a_n}\\to 0\\) \\(\\frac{\\sin(a_n)}{a_n}\\to 1\\) \\(\\frac{\\cos(a_n)}{a_n}\\to 0\\) \\(\\frac{\\sin(a_n)}{a"
    },
    {
        "guid": "c304254e-8c84-4179-a6a8-a78b3bdd633d",
        "model_answer": " Match one of the tools (a)-(e) to the following task: \n           Based on database of texts in different languages learn to recognize the language of a sentence.  Supervised regression, prediction Supervised regression, estimation Supervised classification Unsupervised clustering Unsupervised generative models\n\n```\nimport numpy as np\nimport matplotlib.pyplot as plt\nimport matplotlib.pylab as plt_pylab\nimport matplotlib.linalg as linalg\nimport matplotlib.linalg.linalg2 as linalg2\nimport matplotlib.linalg.linalg3 as linalg3\nimport matplotlib.linalg.linalg4 as linalg4\nimport matplotlib.linalg.linalg5 as linalg5\nimport matplotlib.linalg.linalg6 as linalg6\nimport matplotlib.linalg.linalg7 as linalg7\nimport matplotlib.linalg.linalg8 as linalg8\nimport matplotlib.linalg.linalg9 as linalg9\nimport matplotlib.linalg.linalg10 as linalg10\nimport matplotlib.linalg.linalg11 as linalg11\nimport matplotlib.linalg.linalg12 as linalg12\nimport matplotlib.linalg.linalg13 as linalg13\nimport matplotlib.linalg.linalg14 as linalg14\nimport mat"
    },
    {
        "guid": "6f0d7868-be35-4f47-8770-22999fe667a9",
        "model_answer": "\u00c9crivez un algorithme pour r\u00e9soudre ce probl\u00e8me.\n\u00c9crivez un algorithme pour r\u00e9soudre ce probl\u00e8me.\n\nPour r\u00e9soudre ce probl\u00e8me, il n'est pas une probl\u00e8me.\nPour r\u00e9soudre ce probl\u00e8me, il n'est pas une probl\u00e8me.\nPour r\u00e9soudre ce probl\u00e8me, il n'est pas une probl\u00e8me.\nPour r\u00e9soudre ce probl\u00e8me, il n'est pas une probl\u00e8me.\nPour r\u00e9soudre ce probl\u00e8me, il n'est pas une probl\u00e8me.\nPour r\u00e9soudre ce probl\u00e8me, il n'est pas une probl\u00e8me.\nPour r\u00e9soudre ce probl\u00e8me, il n'est pas une probl\u00e8me.\nPour r\u00e9soudre ce probl\u00e8me, il n'est pas une probl\u00e8me.\nPour r\u00e9soudre ce probl\u00e8me, il n'est pas une probl\u00e8me.\nPour r\u00e9soudre ce probl\u00e8me, il n'est pas une probl\u00e8me.\nPour r\u00e9soudre ce probl\u00e8me, il n'est pas une probl\u00e8me.\nPour r\u00e9soudre ce probl\u00e8me, il n'est pas une probl\u00e8me.\nPour r\u00e9soudre ce probl\u00e8"
    },
    {
        "guid": "32cb1531-16d4-4bd0-871d-09c05f083d33",
        "model_answer": "The float of a fishing rod floats at the surface of water. This floater has a cylindrical \n     shape with a radius $r$, a height $h$ and with an homogeneous mass. The float is standing vertically in water and it moves \n     from top to bottom while always staying partially submerged. In addition to its weight, the float is subject to the \n     Archimedian buoyancy $\u000bec{P_A}$ and at a viscous friction force $\u000bec{F} = -k\\eta\u000bec{v}$. The volumic mass of the float \n     has a value equal to two third of the one of water : $\rho_f= \frac{2}{3}\rho_{eau}$.\n       Determine the differential equation of the float motion. Express the non damped pulsation $\\omega_0$ and the \n     damping coefficient $\\lambda$ as function of the problem data.                                                                                                                                                                                                                                                                                                               "
    },
    {
        "guid": "215d2a69-d6c0-4aca-bf47-70eb2091c3fe",
        "model_answer": "How does a Prime+Probe cache attack works? What information does\n                    it typically reveal to the attacker about the victim code?\n                                                                                                                                                                                                                                                                                                                                "
    },
    {
        "guid": "19799141-5b4f-4239-bc50-dd5c1c14a3e9",
        "model_answer": "Parmi les matrices suivantes, indiquer celles qui sont diagonalisables. Le cas \u00e9ch\u00e9ant, diagonaliser ces matrices en donnant explicitement une matrice diagonale et une matrice de changement de base.\\[A=\\left(\\begin{array}{ccc}2 & 4 & 3\\\\-4 & -6 & -3\\\\3 & 3 & 1\\end{array}\\right)\\,,\\quadC=\\left(\\begin{array}{cccc}5 & 0 & 0 & 0\\\\0 & 5 & 0 & 0\\\\1 & 4 & -3 & 0\\\\-1 & -2 & 0 & -3\\end{array}\\right)\\,,\\quadS=\\left(\\begin{array}{ccc}4 & 0 & -2\\\\2 & 5 & 4\\\\0 & 0 & 5\\end{array}\\right)\\]\nPour toutes les matrices sont diagonalisables, il n'est pas une matrice diagonale et une matrice de changement de base. Si les matrices sont diagonalisables, il n'est pas une matrice diagonale et une matrice de changement de base. Si les matrices sont diagonalisables, il n'est pas une matrice diagonale et une matrice de changement de base. Si les matrices sont diagonalisables, il n'est pas une matrice diagonale et une matrice de changement de base. Si les matrices sont diagonalisables, il n'est pas une matrice diagonale et une matrice de changement de base. Si les matrices sont diagonalisables, il n'est pas une matrice diagonale et une matrice de changement de base. Si les matrices sont diagonalisables, il n'est pas une matrice diagonale et une matrice de changement de base. Si les matrices sont diagonalisables, il n'est pas une matrice diagonale et une matrice de changement de base. Si les matrices sont diagonalisables, il n'est pas une matrice diagonale et une matrice de changement de base. Si les matrices sont di"
    },
    {
        "guid": "f3ca44ac-51a9-4ff7-aec4-7b7d76f4837f",
        "model_answer": "What are the difficulties in measuring the response of a cell in order to calculate its transfer function in absence of an analytical template? Eliminating noise from the measurement Obtaining responses to enough different stimuli from a single cell Maintaining the cell alive for a sufficient amount of time Patch-clamp causes a drift of the threshold over time\n\n[asy]\nunitsize(0.7 cm);\n\npair A,B,C,D,E,F,G,H,I,J,K,L,M,N,O,P,Q,R,S,T,U,V,W,X,Y,Z;\nA = (0,0);\nB = (1,0);\nC = (2,0);\nD = (3,0);\nE = (4,0);\nF = (5,0);\nG = (6,0);\nH = (7,0);\nI = (8,0);\nJ = (9,0);\nK = (10,0);\nL = (11,0);\nM = (12,0);\nN = (13,0);\nO = (14,0);\nP = (15,0);\nQ = (16,0);\nR = (17,0);\nS = (18,0);\nT = (19,0);\nU = (20,0);\nV = (21,0);\nW = (22,0);\nX = (23,0);\nY = (24,0);\nZ = (25,0);\n\ndraw(A--B--C--D--E--F--G--H--I--J"
    },
    {
        "guid": "a559e3e1-2520-4d95-9cc1-7cce4798fea3",
        "model_answer": "A characteristic feature of a projection radiograph is: Poor spatial resolution Lengthy data acquisition Tissue superimposition\n\nI am looking for a way to improve the spatial resolution of a projection radiograph. Specifically, I am looking for a way to improve the spatial resolution of a projection radiograph with tissue superimposition.\n\nI have a few questions:\n\n1. How do I improve the spatial resolution of a projection radiograph with tissue superimposition?\n2. How do I improve the spatial resolution of a projection radiograph with tissue superimposition?\n3. How do I improve the spatial resolution of a projection radiograph with tissue superimposition?\n4. How do I improve the spatial resolution of a projection radiograph with tissue superimposition?\n5. How do I improve the spatial resolution of a projection radiograph with tissue superimposition?\n6. How do I improve the spatial resolution of a projection radiograph with tissue superimposition?\n7. How do I improve the spatial resolution of a projection radiograph with tissue superimposition?\n8. How do I improve the spatial resolution of a projection radiograph with tissue superimposition?\n9. How do I improve the spatial resolution of a projection radiograph with tissue superimposition?\n10. How do I improve the spatial resolution of a projection radiograph with tissue superimposition?\n11. How do I improve the spatial resolution of a projection radiograph with tissue superimposition?\n12. How do I improve the spatial resolution of a projection radiograph with tissue"
    },
    {
        "guid": "52f78310-1458-4ad2-9605-e99a10e73550",
        "model_answer": "What advantages (3) do scoring procedures such as the one proposed by Druckmann et al. (2007) have over simple least square distance based procedures? They account for variability in the experimental data and penalize the model according to experimental variability They can focus on reproduction of some features rather than perfect reproduction of the experimental data They do not sum the features The distance is expressed in meaningful unit units, rather than in terms of the number of features\n\n[asy]\nunitsize(1 cm);\n\npair A,B,C,D,E,F,G,H,I,J,K,L,M,N,O,P,Q,R,S,T,U,V,W,X,Y,Z;\n\nA = (0,0);\nB = (0,1);\nC = (0,2);\nD = (0,3);\nE = (0,4);\nF = (0,5);\nG = (0,6);\nH = (0,7);\nI = (0,8);\nJ = (0,9);\nK = (0,10);\nL = (0,11);\nM = (0,12);\nN = (0,13);\nO = (0,14);\nP = (0,15);\nQ = (0,16);\nR = (0,17);\nS = (0,18);\nT = (0,19);\nU = (0,20);\nV = (0,21);\nW = (0,22);\nX = (0,23);\nY = (0,24);\nZ = (0,25);\ndraw(A--B--C--D--E--"
    },
    {
        "guid": "70f8efa0-1816-445b-a053-cf92ee323bab",
        "model_answer": "Natural frequency of precession and Larmor frequency are... Different names for the same frequency Two different frequencies for the same precession Two different frequencies for the same Larmor Two different frequencies for the same precession Two different frequencies for the same Larmor Two different frequencies for the same Larmor Two different frequencies for the same Larmor Two different frequencies for the same Larmor Two different frequencies for the same Larmor Two different frequencies for the same Larmor Two different frequencies for the same Larmor Two different frequencies for the same Larmor Two different frequencies for the same Larmor Two different frequencies for the same Larmor Two different frequencies for the same Larmor Two different frequencies for the same Larmor Two different frequencies for the same Larmor Two different frequencies for the same Larmor Two different frequencies for the same Larmor Two different frequencies for the same Larmor Two different frequencies for the same Larmor Two different frequencies for the same Larmor Two different frequencies for the same Larmor Two different frequencies for the same Larmor Two different frequencies for the same Larmor Two different frequencies for the same Larmor Two different frequencies for the same Larmor Two different frequencies for the same Larmor Two different frequencies for the same Larmor Two different frequencies for the same Larmor Two different frequencies for the same Larmor Two different frequencies for the same Larmor Two different frequencies for the same Larmor Two different frequencies for the same Larmor Two different frequencies for the same Larmor Two different frequencies for the same Larmor Two different frequencies for the same Larmor Two different frequencies for the same Larmor Two different frequencies for the same L"
    },
    {
        "guid": "98df46d4-9b69-4702-8e58-6e4c2fedc94e",
        "model_answer": "Pour chacun des syst\\`emes suivants:\\begin{itemize}\\item [1)] \\'Ecrire la matrice augment\\'ee.\\item [2)] Mettre la matrice augment\\'ee sous forme \\'echelonn\\'ee r\\'eduite.\\item [3)] Identifier les variables de bases et les variables libres, et \\'ecrire la solution g\\'en\\'erale.$\\left\\{\\begin{array}{rrrrrrrrrrr}x_1 & + & x_2 & + & x_3 & + & x_4 & + & x_5 & = & 2 \\\\x_1 & + & x_2 & + & x_3 & + & 2 x_4 & + & 2 x_5 & = & 3 \\\\x_1 & + & x_2 & + & x_3 & + & 2 x_4 & + & 3 x_5 & = & 2 \\\\\\end{array}\\right.$\\end{itemize}\\]Pour chacun des syst\\`emes suivants:\\begin{itemize}\\item [1)] \\'Ecrire la matrice augment\\'ee.\\item [2)] Mettre la matrice augment\\'ee sous forme \\'echelonn\\'ee r\\'eduite.\\item [3)] Identifier les variables de bases et les variables libres, et \\'ecrire la solution g\\'en\\'erale.$\\left\\{\\begin{array}{rrrrrrrrrrr}x_1 & + & x_2 & + & x_3 & + & x_4 & + & x_5 & = & 2 \\\\x_1 & + & x_2 & + & x_3 & + & 2 x_4 & + & 2 x_5 & = & 3 \\\\x_1 & + & x_2 & + & x_3 & + & 2 x_4 & + & 3 x_5 & = & 2 \\\\\\end{array}\\right.$\\end{itemize}\\]Pour chacun des syst\\`emes suivants:\\begin{itemize}\\item [1)] \\'Ecrire la matrice augment\\'ee.\\item [2)] Mettre la matrice augment\\'ee sous forme \\'echelonn\\'ee r\\'eduite.\\"
    },
    {
        "guid": "59c0251a-f677-46d1-aff0-a5435e62230c",
        "model_answer": "Indiquer pour chaque \u00e9nonc\u00e9 s'il est vrai ou faux et justifier bri\u00e8vement votre r\u00e9ponse.\\begin{enumerate}[a)]\\item La matrice d'une forme quadratique est sym\u00e9trique.\\item Les axes principaux d'une forme quadratique sont les vecteurs propres de $A$.\\item Une forme quadratique strictement positive satisfait $Q(x)>0$,$\\forall x\\in\\mathbb{R}^n$.\\item Si les valeurs propres d'une matrice sym\u00e9trique $A$ sont toutes strictement positives, alors la forme quadratique $x^{T}Ax$ est d\u00e9finie positive. \\item L'expression $\\|x\\|^2$ est une forme quadratique.\\end{enumerate}\n\\[\\begin{enumerate}[a]\\item La matrice d'une forme quadratique est sym\u00e9trique.\\item Les axes principaux d'une forme quadratique sont les vecteurs propres de $A$.\\item Une forme quadratique strictement positive satisfait $Q(x)>0$,$\\forall x\\in\\mathbb{R}^n$.\\item Si les valeurs propres d'une matrice sym\u00e9trique $A$ sont toutes strictement positives, alors la forme quadratique $x^{T}Ax$ est d\u00e9finie positive. \\item L'expression $\\|x\\|^2$ est une forme quadratique.\\end{enumerate}\n\\[\\begin{enumerate}[a]\\item La matrice d'une forme quadratique est sym\u00e9trique.\\item Les axes principaux d'une forme quadratique sont les vecteurs propres de $A$.\\item Une forme quadratique strictement positive satisfait $Q(x)>0$,$\\forall x\\in\\mathbb{R}^n$.\\item Si les valeurs propres d'une matrice sym\u00e9trique $A$ sont toutes strictement positives, al"
    },
    {
        "guid": "13739c83-35d1-4fec-867c-98bd69f9ae73",
        "model_answer": "You are doing your ML project. It is a regression task under a square loss. Your neighbor uses linear regression and least squares. You are smarter. You are using a neural net with 10 layers and activations functions $f(x)=3 x$. You have a powerful laptop but not a supercomputer. You are betting your neighbor a beer at Satellite who will have a substantially better scores. However, at the end it will essentially be a tie, so we decide to have two beers and both pay. What is the reason for the outcome of this bet? Because we use exactly the same scheme. Because it is almost impossible to train a network with 10 layers without a supercomputer. Because I should have used more layers. Because I should have used only one layer. Because I should have used only one layer. Because I should have used only one layer. Because I should have used only one layer. Because I should have used only one layer. Because I should have used only one layer. Because I should have used only one layer. Because I should have used only one layer. Because I should have used only one layer. Because I should have used only one layer. Because I should have used only one layer. Because I should have used only one layer. Because I should have used only one layer. Because I should have used only one layer. Because I should have used only one layer. Because I should have used only one layer. Because I should have used only one layer. Because I should have used only one layer. Because I should have used only one layer. Because I should have used only one layer. Because I should have used only one layer. Because I should have used only one layer. Because I should have used only one layer. Because I should have used only one layer. Because I should have used only one layer. Because I should have used only one layer. Because I should have used only one layer. Because I should have used only one layer. Because I should have used only one layer. Because I should have used only one layer. Because I should have used only one layer. Because I should have used only one layer. Because I should have used only one layer. Because I should have used only one layer. Because I should"
    },
    {
        "guid": "dc243fc6-5295-426f-ace7-c1594dcb4d59",
        "model_answer": "What tools are typically used to study gene regulatory networks? Computational modeling Genetic knockouts Patch-clamp Behavioral studies\n\nIf you are looking for tools to study gene regulatory networks, you have come to the right place. Gene regulatory networks (GNCs) are networks of genes that regulate the expression of genes in different tissues and cell types. GNCs are thought to play a key role in the regulation of gene expression in many different tissues and cell types.\n\nGNCs are thought to play a key role in the regulation of gene expression in many different tissues and cell types. GNCs are thought to play a key role in the regulation of gene expression in many different tissues and cell types.\n\nGNCs are thought to play a key role in the regulation of gene expression in many different tissues and cell types. GNCs are thought to play a key role in the regulation of gene expression in many different tissues and cell types.\n\nGNCs are thought to play a key role in the regulation of gene expression in many different tissues and cell types. GNCs are thought to play a key role in the regulation of gene expression in many different tissues and cell types.\n\nGNCs are thought to play a key role in the regulation of gene expression in many different tissues and cell types. GNCs are thought to play a key role in the regulation of gene expression in many different tissues and cell types.\n\nGNCs are thought to play a key role in the regulation of gene expression in many different tissues and cell types. GNCs"
    },
    {
        "guid": "2f7b092b-e05b-4b04-a99c-b9963f8e3032",
        "model_answer": "We consider an oscillating electromagnetic field that exhibits phase fluctuations, which model, for example, the output of a realistic RF signal generator or a laser. Assume that the field is given by [mathjaxinline]E(t)=E_{0} e^{-i \\omega_{0} t+i \\phi(t)},[/mathjaxinline] where the phase [mathjaxinline]\\phi(t)[/mathjaxinline] is a Wiener process with diffusion constant [mathjaxinline]D[/mathjaxinline] [mathjaxinline]\\left\\langle e^{i \\phi\\left(t_{1}\\right)-i \\phi\\left(t_{2}\\right)}\\right\\rangle=e^{-\\frac{1}{2} D^2\\left|t_{1}-t_{2}\\right|}[/mathjaxinline] [mathjaxinline]\\left\\langle e^{i \\phi\\left(t_{1}\\right)-i \\phi\\left(t_{2}\\right)}\\right\\rangle=e^{-\\frac{1}{2} D\\left|t_{1}-t_{2}\\right|^2}[/mathjaxinline] [mathjaxinline]\\left\\langle e^{i \\phi\\left(t_{1}\\right)-i \\phi\\left(t_{2}\\right)}\\right\\rangle=e^{-\\frac{1}{2} D^2\\left|t_{1}-t_{2}\\right|^2}[/mathjaxinline] [mathjaxinline]\\left\\langle e^{i \\phi\\left(t_{1}\\right)-i \\phi\\left(t_{2}\\right)}\\right\\rangle=e^{-\\frac{1}{2} D\\left|t_{1}-t_{2}\\right|}[/mathjaxinline] [mathjaxinline]\\left\\langle e^{i \\phi\\left(t_{1}\\right)-i \\phi\\left(t_{2}\\right)}\\right\\rangle=e^{-\\frac{1}{2} D\\left|t_{1}-t_{2}\\right|^2}[/mathjaxinline] [mathjaxinline]\\left\\langle e^{i \\phi\\left(t_{1}\\right)-i \\phi\\left(t_{2}\\right)}\\right\\rangle=e^{-\\frac{1}{2} D\\left|t_{1}-t_{2}\\right|^2}[/mathjaxinline] [mathjaxinline]\\left\\langle e^{i \\phi\\left(t_{1}\\right)-i \\phi\\left(t_{2}\\right)}\\right\\rangle=e^{-\\frac{1}{2} D\\left|t_{1}-t_{2}\\right|^2}[/mathjaxinline] [mathjaxinline]\\left\\langle e^{i \\phi\\left(t_{1}\\right)-i \\phi\\left(t_{2}\\right)}\\right\\rangle=e^{-\\frac{1}{2} D\\left|t_{1}-t_{2}\\right|^"
    },
    {
        "guid": "23ffa81e-c9d4-4c01-87ef-d88bb108587b",
        "model_answer": "Which statements about cable theory are true? The conductance for each ion stays the same all along the axon and dendrites It quantifies the propagation of a signal along the axon and dendrites The change in voltage over the distance is related to the change in voltage over time The neuron is discretized to form several coupled compartments corresponding to parts of the axon and dendrites The axon and dendrites are connected by axonal axons and dendrites The axon and dendrites are connected by axonal axons and dendrites The axon and dendrites are connected by axonal axons and dendrites The axon and dendrites are connected by axonal axons and dendrites The axon and dendrites are connected by axonal axons and dendrites The axon and dendrites are connected by axonal axons and dendrites The axon and dendrites are connected by axonal axons and dendrites The axon and dendrites are connected by axonal axons and dendrites The axon and dendrites are connected by axonal axons and dendrites The axon and dendrites are connected by axonal axons and dendrites The axon and dendrites are connected by axonal axons and dendrites The axon and dendrites are connected by axonal axons and dendrites The axon and dendrites are connected by axonal axons and dendrites The axon and dendrites are connected by axonal axons and dendrites The axon and dendrites are connected by axonal axons and dendrites The axon and dendrites are connected by axonal axons and dendrites The axon and dendrites are connected by axonal"
    },
    {
        "guid": "2fabe332-48ef-433b-9b1c-b4e486180637",
        "model_answer": "Assume that we have a data matrix $\\mathbf{X}$ of dimension $D \\times N$ as usual. Suppose that its SVD is of the from $\\mathbf{X}=\\mathbf{U S V}^{\\top}$, where $\\mathbf{S}$ is a diagonal matrix with $s_{1}=N$ and $s_{2}=s_{3}=\\cdots=s_{D}=1$. Assume that we want to compress the data from $D$ to 1 dimensions via a linear transform represented by a $1 \\times D$ matrix $\\mathbf{C}$ and reconstruct then via $D \\times 1$ matrix $R$. Let $\\hat{\\mathbf{X}}=\\mathbf{R} \\mathbf{C X}$ be the reconstruction. What is the smallest value we can achieve for $\\|\\mathbf{X}-\\hat{\\mathbf{X}}\\|_{F}^{2}$? (a) $D$ (b) $D-1$ (c) $N-D$ (d) $N-D+1$ (e) $N-D-1$ (f) $N-1$ (g) $N$ (h) $N+1$ (i) $N+1+1$ (j) $N+1+1+1$ (k) $N+1+1+1+1+1+1+1+1+1+1+1+1+1+1+1+1+1+1+1+1+1+1+1+1+1+1+1+1+1+1+1+1+1+1+1+1+1+1+1+1+1+1+1+1+1+1+1+1+1+1+1+1+1+1+1+1+1+1+1+1+1+1+1+1+1+1+1+1+1+1+1+1+1+1+1+1+1+1+1+1+1+1+1+1+1+1+1+1+1+1+1+1+1+1+1+1+1+1+1+1+1+1+1+1+1+1+1+1+1+1+1+1+1+1+1+1+1+1+1+1+1+1+1+1+1+1+1+1+1+1+1+1+"
    },
    {
        "guid": "1986353f-b780-4b31-94d6-fd9af077fb07",
        "model_answer": "What is the difference between genetics and epigenetics? Genetic characteristics are heritable, but not epigenetic one Epigenetic characteristics vary between cell types, but genetic characteristics do not Differences in epigenetics do not influence gene expression whereas genetic variability does All of the above.\n\n[asy]\nunitsize(0.8 cm);\n\npair A, B, C, D, E, F, G, H, I, J, K, L, M, N, O, P, Q, R, S, T, U, V, W, X, Y, Z;\n\nA = (0,0);\nB = (0,1);\nC = (0,2);\nD = (0,3);\nE = (0,4);\nF = (0,5);\nG = (0,6);\nH = (0,7);\nI = (0,8);\nJ = (0,9);\nK = (0,10);\nL = (0,11);\nM = (0,12);\nN = (0,13);\nO = (0,14);\nP = (0,15);\nQ = (0,16);\nR = (0,17);\nS = (0,18);\nT = (0,19);\nU = (0,20);\nV = (0,21);\nW = (0,22);\nX = (0,23);\nY = (0,24);\nZ = (0,25);\ndraw(A--B--C--D--E--F--G--H--I--"
    },
    {
        "guid": "b1ea7aed-566b-4da0-803d-f29fc4cf50e1",
        "model_answer": "Soit $A$ une matrice de taille $n\\times n$. Indiquer si les affirmationssuivantes sont vraies ou fausses (justifier).  Pour tout matrice inversible \\(P\\) de taille \\(n\\times n\\),  \\(\\lambda\\)est une valeur propre de \\(A\\) si et seulement si \\(\\lambda\\) est une valeur proprede \\(P^{-1}AP\\).   Pour tout matrice inversible \\(P\\) de taille \\(n\\times n\\),  \\(\\lambda\\)est une valeur propre de \\(A\\) si et seulement si \\(\\lambda\\) est une valeur proprede \\(P^{-1}AP\\).\n\nPour tout matrice inversible \\(P\\) de taille \\(n\\times n\\),  \\(\\lambda\\)est une valeur propre de \\(A\\) si et seulement si \\(\\lambda\\) est une valeur proprede \\(P^{-1}AP\\).\n\nPour tout matrice inversible \\(P\\) de taille \\(n\\times n\\),  \\(\\lambda\\)est une valeur propre de \\(A\\) si et seulement si \\(\\lambda\\) est une valeur proprede \\(P^{-1}AP\\).\n\nPour tout matrice inversible \\(P\\) de taille \\(n\\times n\\),  \\(\\lambda\\)est une valeur propre de \\(A\\) si et seulement si \\(\\lambda\\) est une valeur proprede \\(P^{-1}AP\\).\n\nPour tout matrice inversible \\(P\\) de taille \\(n\\times n\\),  \\(\\lambda\\)est une valeur propre de \\(A\\) si et seulement si \\(\\lambda\\)"
    },
    {
        "guid": "d563f81d-6eef-4e06-b40c-e00352d5aa78",
        "model_answer": "Montrer que les op\\'erations \\'el\\'ementaires sur les lignes dites \"valides\" (\u00e0savoir, l'ajout d'une ligne \u00e0 une autre, l'\u00e9change de deux lignes, et lamultiplication d'une ligne par un r\u00e9el non nul) transforment un syst\\`emelin\\'eaire en un syst\\`eme \\'equivalent.\\`\\[\\begin{pmatrix} 1 \\\\ 2 \\\\ 3 \\\\ 4 \\\\ 5 \\\\ 6 \\\\ 7 \\\\ 8 \\\\ 9 \\\\ 10 \\\\ 11 \\\\ 12 \\\\ 13 \\\\ 14 \\\\ 15 \\\\ 16 \\\\ 17 \\\\ 18 \\\\ 19 \\\\ 20 \\\\ 21 \\\\ 22 \\\\ 23 \\\\ 24 \\\\ 25 \\\\ 26 \\\\ 27 \\\\ 28 \\\\ 29 \\\\ 30 \\\\ 31 \\\\ 32 \\\\ 33 \\\\ 34 \\\\ 35 \\\\ 36 \\\\ 37 \\\\ 38 \\\\ 39 \\\\ 40 \\\\ 41 \\\\ 42 \\\\ 43 \\\\ 44 \\\\ 45 \\\\ 46 \\\\ 47 \\\\ 48 \\\\ 49 \\\\ 50 \\\\ 51 \\\\ 52 \\\\ 53 \\\\ 54 \\\\ 55 \\\\ 56 \\\\ 57 \\\\ 58 \\\\ 59 \\\\ 60 \\\\ 61 \\\\ 62 \\\\ 63 \\\\ 64 \\\\ 65 \\\\ 66 \\\\ 67 \\\\ 68 \\\\ 69 \\\\ 70 \\\\ 71 \\\\ 72 \\\\ 73 \\\\ 74 \\\\ 75 \\\\ 76 \\\\ 77 \\\\ 78 \\\\ 79 \\\\ 80 \\\\ 81 \\\\ 82 \\\\ 83 \\\\ 84 \\\\ 85 \\\\ 86 \\\\ 87 \\\\ 88 \\\\ 89 \\\\ 90 \\\\ 91 \\\\ 92 \\\\ 93 \\\\ 94 \\\\ 95 \\\\ 96 \\\\ 97 \\\\ 98 \\\\ 99 \\\\ 100 \\\\ 101 \\\\ 102 \\\\ 103 \\\\ 104 \\\\ 105 \\\\ 106 \\\\ 107 \\\\ 108 \\\\ 109 \\\\ 110 \\\\ 111 \\\\ 112 \\\\ 113 \\\\ 114 \\\\ 115 \\\\ 116 \\\\ 117 \\\\ 118 \\\\ 119 \\\\ 120 \\\\ 121 \\\\ 122 \\\\ 123 \\\\ 124 \\\\ 125 \\\\ 126 \\\\ 127 \\\\ 128 \\\\ 129 \\\\ 130 \\\\ 131 \\\\ 132 \\\\ 133 \\\\ 134 \\\\ 135 \\\\ 136 \\\\ 137 \\\\ 138 \\\\ 139 \\\\ 140 \\\\ 141 \\\\ 142 \\\\ 143 \\\\ 144 \\\\ 145"
    },
    {
        "guid": "c1bc4cc6-e6af-4bb6-86c2-1dee8ec49ad2",
        "model_answer": "Consider (u,w) coordinate system: on the u-nullcline, arrows are always vertical on the u-nullcline, arrows point always vertically upward on the u-nullcline, arrows are always horizontal on the u-nullcline, arrows point always to the left on the u-nullcline, arrows point always to the right on the u-nullcline, and arrows point always to the top on the u-nullcline.\n\nIf we want to draw a line from point (u,w) to point (x,y) on the u-nullcline, how can we do it?\n\n[asy]\nunitsize(1 cm);\n\npair A,B,C,D,E,F,G,H,I,J,K,L,M,N,O,P,Q,R,S,T,U,V,W,X,Y,Z;\nA = (0,0);\nB = (1,0);\nC = (2,0);\nD = (3,0);\nE = (4,0);\nF = (5,0);\nG = (6,0);\nH = (7,0);\nI = (8,0);\nJ = (9,0);\nK = (10,0);\nL = (11,0);\nM = (12,0);\nN = (13,0);\nO = (14,0);\nP = (15,0);\nQ = (16,0);\nR = (17,0);\nS = (18,0);\nT = (19,0);\nU = (20,0);\nV = (21"
    },
    {
        "guid": "f732d470-1631-4a0d-b1f6-51e937cf55be",
        "model_answer": "Quelle est l'expression de l'\u00e9nergie magn\u00e9tique pour un volume infinit\u00e9simal? (une seule r\u00e9ponse possible) \\( dW_{mag} = \\int_{0}^{H} H*dB*dV \\) \\( dW_{mag} = \\int_{0}^{B} B*dH*dV \\) \\( dW_{mag} = \\int_{0}^{B} H*dB*dV \\) \\( dW_{mag} = \\int_{0}^{H} B*dH*dV \\) \\( dW_{mag} = \\int_{0}^{H} B*dH*dV \\) \\( dW_{mag} = \\int_{0}^{H} B*dH*dV \\) \\( dW_{mag} = \\int_{0}^{H} B*dH*dV \\) \\( dW_{mag} = \\int_{0}^{H} B*dH*dV \\) \\( dW_{mag} = \\int_{0}^{H} B*dH*dV \\) \\( dW_{mag} = \\int_{0}^{H} B*dH*dV \\) \\( dW_{mag} = \\int_{0}^{H} B*dH*dV \\) \\( dW_{mag} = \\int_{0}^{H} B*dH*dV \\) \\( dW_{mag} = \\int_{0}^{H} B*dH*dV \\) \\( dW_{mag} = \\int_{0}^{H} B*dH*dV \\) \\( dW_{mag} = \\int_{0}^{H} B*dH*dV \\) \\( dW_{mag} = \\int_{0}^{H} B*dH*dV \\) \\( dW_{mag} = \\int_{0}"
    },
    {
        "guid": "88379c2b-4bda-41c0-b1c1-e44dc19ea14b",
        "model_answer": "Sometimes, in Cl plasma etching, a corrosion phenomenon is observed in Al etching under the form of chlorine-containing residues remaining on the film sidewalls. Which of the following is a correct approach to avoid this problem? Immersing the wafer in a PGMEA developer Gently blowing the wafer surface with nitrogen gun to create AlN gas Dipping before etching the wafer in diluted acetone solution Exposing the etched structure to a fluorine plasma immediately after the Cl plasma etching.\n\n[asy]\nsize(150);\n\npair A,B,C,D,E,F,G,H,I,J,K,L,M,N,O,P,Q,R,S,T,U,V,W,X,Y,Z;\nA = (0,0);\nB = (0,1);\nC = (0,2);\nD = (0,3);\nE = (0,4);\nF = (0,5);\nG = (0,6);\nH = (0,7);\nI = (0,8);\nJ = (0,9);\nK = (0,10);\nL = (0,11);\nM = (0,12);\nN = (0,13);\nO = (0,14);\nP = (0,15);\nQ = (0,16);\nR = (0,17);\nS = (0,18);\nT = (0,19);\nU = (0,20);\nV = (0,21);\nW = (0,22);\nX = (0,23);\nY = (0,24);\nZ = (0,25);\ndraw(A--B--C--D--E--F--G--H--I--J--K"
    },
    {
        "guid": "ec128ef4-97e2-4998-a41c-e6eab0953c8c",
        "model_answer": "The \"Consensus-Based Total-Order Broadcast\" algorithm transforms a consensus abstraction (together with a reliable broadcast abstraction) into a total-order broadcast abstraction. Describe a transformation between these two primitives in the other direction, that is, implement a (uniform) consensus abstraction from a (uniform) total-order broadcast abstraction.\n\n[asy]\nunitsize(0.5 cm);\n\npair A,B,C,D,E,F,G,H,I,J,K,L,M,N,O,P,Q,R,S,T,U,V,W,X,Y,Z;\n\nA = (0,0);\nB = (0,1);\nC = (0,2);\nD = (0,3);\nE = (0,4);\nF = (0,5);\nG = (0,6);\nH = (0,7);\nI = (0,8);\nJ = (0,9);\nK = (0,10);\nL = (0,11);\nM = (0,12);\nN = (0,13);\nO = (0,14);\nP = (0,15);\nQ = (0,16);\nR = (0,17);\nS = (0,18);\nT = (0,19);\nU = (0,20);\nV = (0,21);\nW = (0,22);\nX = (0,23);\nY = (0,24);\nZ = (0,25);\n\ndraw(A--B--C--D--E--F--G--H--I--"
    },
    {
        "guid": "2b3de139-3757-4f15-9b48-e785fd51c3f4",
        "model_answer": "What is the main difference between PET and SPECT? The detection ring used in PET and SPECT are different PET scan begins with the administration of a radiopharmaceutical PET scan requires a longer time for data collection PET scan uses positron-emitting radioisotope instead of single-photon emitters SPECT uses a two-photon emitters SPECT does not use positron-emitting radioisotope SPECT uses a two-photon emitters PET scan does not use positron-emitting radioisotope PET scan uses positron-emitting radioisotope PET scan uses positron-emitting radioisotope PET scan uses positron-emitting radioisotope PET scan uses positron-emitting radioisotope PET scan uses positron-emitting radioisotope PET scan uses positron-emitting radioisotope PET scan uses positron-emitting radioisotope PET scan uses positron-emitting radioisotope PET scan uses positron-emitting radioisotope PET scan uses positron-emitting radioisotope PET scan uses positron-emitting radioisotope PET scan uses positron-emitting radioisotope PET scan uses positron-emitting radioisotope PET scan uses positron-emitting radioisotope PET scan uses positron-emitting radioisotope PET scan uses positron-emitting radioisotope PET scan uses positron-emitting radioisotope PET scan uses positron-emitting radioisotope PET scan uses positron-emitting radioisotope PET scan uses positron-emitting radioisotope PET scan uses positron-emitting radioisotope"
    },
    {
        "guid": "19799141-5b4f-4239-bc50-dd5c1c14a3e9",
        "model_answer": "Parmi les matrices suivantes, indiquer celles qui sont diagonalisables. Le cas \u00e9ch\u00e9ant, diagonaliser ces matrices en donnant explicitement une matrice diagonale et une matrice de changement de base.\\[A=\\left(\\begin{array}{ccc}2 & 4 & 3\\\\-4 & -6 & -3\\\\3 & 3 & 1\\end{array}\\right)\\,,\\quadC=\\left(\\begin{array}{cccc}5 & 0 & 0 & 0\\\\0 & 5 & 0 & 0\\\\1 & 4 & -3 & 0\\\\-1 & -2 & 0 & -3\\end{array}\\right)\\,,\\quadS=\\left(\\begin{array}{ccc}4 & 0 & -2\\\\2 & 5 & 4\\\\0 & 0 & 5\\end{array}\\right)\\]Pour toutes les matrices sont diagonalisables, il existe une matrice diagonale et une matrice de changement de base.\\[A=\\left(\\begin{array}{ccc}2 & 4 & 3\\\\-4 & -6 & -3\\\\3 & 3 & 1\\end{array}\\right)\\,,\\quadC=\\left(\\begin{array}{cccc}5 & 0 & 0 & 0\\\\0 & 5 & 0 & 0\\\\1 & 4 & -3 & 0\\\\-1 & -2 & 0 & -3\\end{array}\\right)\\,,\\quadS=\\left(\\begin{array}{ccc}4 & 0 & -2\\\\2 & 5 & 4\\\\0 & 0 & 5\\end{array}\\right)\\]Pour toutes les matrices sont diagonalisables, il existe une matrice diagonale et une matrice de changement de base.\\[A=\\left(\\begin{array}{ccc}2 & 4 & 3\\\\-4 & -6 & -3\\\\3 & 3 & 1\\end{array}\\right)\\,,\\quadC=\\left(\\begin{array}{cccc}5 & 0 & 0 & 0\\\\0 & 5 & 0 & 0\\\\1 & 4 & -3 & 0\\\\-1 & -2 & 0 & -3\\end"
    },
    {
        "guid": "45f4f919-77fb-4bbc-92f6-172fec8f4a92",
        "model_answer": "Did you write a thread and at least one comment? Yes No\n\n[![enter image description here](https://i.stack.imgur.com/mVnh.png)](https://i.stack.imgur.com/mVnh.png)\n\n```\n#include <stdio.h>\n#include <stdlib.h>\n#include <string.h>\n\n#include <unistd.h>\n\n#include <sys/types.h>\n\n#include <sys/stat.h>\n\n#include <sys/types.h>\n\n#include <sys/stat.h>\n\n#include <unistd.h>\n\n#include <sys/types.h>\n\n#include <sys/stat.h>\n\n#include <sys/types.h>\n\n#include <sys/stat.h>\n\n#include <sys/types.h>\n\n#include <sys/stat.h>\n\n#include <sys/types.h>\n\n#include <sys/stat.h>\n\n#include <sys/types.h>\n\n#include <sys/stat.h>\n\n#include <sys/types.h>\n\n#include <sys/stat.h>\n\n#include <sys/types.h>\n\n#include <sys/stat.h>\n\n#include <"
    },
    {
        "guid": "f1d23839-38a5-46f6-946d-c0a11cc6c4e8",
        "model_answer": "The tissue contrast in MRI is obtained with differences in... Gyromagnetic ratio Spin-spin and spin-lattice relaxation constants Carbon and nitrogen abundance Magnetic field inhomogeneity in tissues Magnetic field inhomogeneity in the atmosphere Magnetic field inhomogeneity in the atmosphere Magnetic field inhomogeneity in the atmosphere Magnetic field inhomogeneity in the atmosphere Magnetic field inhomogeneity in the atmosphere Magnetic field inhomogeneity in the atmosphere Magnetic field inhomogeneity in the atmosphere Magnetic field inhomogeneity in the atmosphere Magnetic field inhomogeneity in the atmosphere Magnetic field inhomogeneity in the atmosphere Magnetic field inhomogeneity in the atmosphere Magnetic field inhomogeneity in the atmosphere Magnetic field inhomogeneity in the atmosphere Magnetic field inhomogeneity in the atmosphere Magnetic field inhomogeneity in the atmosphere Magnetic field inhomogeneity in the atmosphere Magnetic field inhomogeneity in the atmosphere Magnetic field inhomogeneity in the atmosphere Magnetic field inhomogeneity in the atmosphere Magnetic field inhomogeneity in the atmosphere Magnetic field inhomogeneity in the atmosphere Magnetic field inhomogeneity in the atmosphere Magnetic field inhomogeneity in the atmosphere Magnetic field inhomogeneity in the atmosphere Magnetic field inhomogeneity in the atmosphere Magnetic field inhomogeneity in the atmosphere Magnetic field inhomogeneity in the atmosphere Magnetic field inhomogeneity in the atmosphere Magnetic field inhomogeneity in the atmosphere Magnetic field inhomogeneity in the atmosphere Magnetic field inhomogeneity in the atmosphere Magnetic field inhomogeneity in the atmosphere Magnetic field inhomogeneity in the atmosphere Magnetic field inhomogeneity in the atmosphere Magnetic field inhomogeneity in the atmosphere Magnetic field inhomogeneity in the atmosphere Magnetic field inhomogeneity in the atmosphere Magnetic field inhom"
    },
    {
        "guid": "d12be254-279f-4223-852c-9bb0791bb816",
        "model_answer": "La distance entre le Soleil et V\u00e9nus est de \\(108.2 \\cdot 10^6\\) km. Cette distance s'\u00e9crit aussi: \\(1.082 \\cdot 10^{8}\\) m \\(108.2 \\cdot 10^{10}\\) m \\(1.082 \\cdot 10^{11}\\) m \\(108.2 \\cdot 10^{12}\\) m \\(108.2 \\cdot 10^{13}\\) m \\(108.2 \\cdot 10^{14}\\) m \\(108.2 \\cdot 10^{15}\\) m \\(108.2 \\cdot 10^{16}\\) m \\(108.2 \\cdot 10^{17}\\) m \\(108.2 \\cdot 10^{18}\\) m \\(108.2 \\cdot 10^{19}\\) m \\(108.2 \\cdot 10^{20}\\) m \\(108.2 \\cdot 10^{21}\\) m \\(108.2 \\cdot 10^{22}\\) m \\(108.2 \\cdot 10^{23}\\) m \\(108.2 \\cdot 10^{24}\\) m \\(108.2 \\cdot 10^{25}\\) m \\(108.2 \\cdot 10^{26}\\) m \\(108.2 \\cdot 10^{27}\\) m \\(108.2 \\cdot 10^{28}\\) m \\(108.2 \\cdot 10^{29}\\) m \\(108.2 \\cdot 10^{30}\\) m \\(108.2 \\cdot 10^{31}\\) m \\(108.2 \\cdot 10^{32}\\) m \\(108.2 \\cdot 10^{33}\\) m \\(108.2 \\cdot 10^{34}\\) m \\("
    },
    {
        "guid": "6a7100d1-64e2-426d-b762-62bafa8b9d55",
        "model_answer": "What characterizes the process of releasing neurotransmitters (2)? Neurotransmitters are packaged in vesicles called quanta All synapses have the same number of release sites (N) One quantum generates a miniature end plate potential, which is the smallest amount of stimulation that one neuron can send to another neuron The probability of one site releasing a vesicle upon stimulation is always 1/N The probability of one site releasing a vesicle upon stimulation is always 1/N The probability of one site releasing a vesicle upon stimulation is always 1/N The probability of one site releasing a vesicle upon stimulation is always 1/N The probability of one site releasing a vesicle upon stimulation is always 1/N The probability of one site releasing a vesicle upon stimulation is always 1/N The probability of one site releasing a vesicle upon stimulation is always 1/N The probability of one site releasing a vesicle upon stimulation is always 1/N The probability of one site releasing a vesicle upon stimulation is always 1/N The probability of one site releasing a vesicle upon stimulation is always 1/N The probability of one site releasing a vesicle upon stimulation is always 1/N The probability of one site releasing a vesicle upon stimulation is always 1/N The probability of one site releasing a vesicle upon stimulation is always 1/N The probability of one site releasing a vesicle upon stimulation is always 1/N The probability of one site releasing a vesicle upon stimulation is always 1/N The probability of one site releasing a vesicle upon stimulation is always 1/N The probability of one site releasing a vesicle upon stimulation is always 1/N The probability of one site releasing a vesicle upon stimulation is always 1/N The probability of one site releasing a ves"
    },
    {
        "guid": "458183ae-aef2-4798-b64d-b7de727c5300",
        "model_answer": "Soit \\(x_0\\in \\bR\\) et \\(f\\) une fonction poss\u00e9dant, pour tout \\(n\\),\nun d\u00e9veloppement limit\u00e9 d'ordre\n\\(n\\) en \\(x_0\\): \\(f(x)=p_n(x-x_0)+R_n(x)\\) \n (\\(p_n\\) est un polyn\u00f4me d'ordre \\(n\\)). \nVrai ou faux? Si \\(R_n(x)\\to 0\\) lorsque \\(n\\to\\infty\\), alors \\(f\\) admet un\nd\u00e9veloppement de Taylor autour \\(x_0\\). Si \\(p_n(x-x_0)\\to 0\\) lorsque \\(n\\to\\infty\\), alors \\(f\\) admet un\nd\u00e9veloppement de Taylor en \\(x_0\\). Si \\(p_n(x-x_0)\\to 0\\) lorsque \\(n\\to\\infty\\), alors \\(f\\) admet un\nd\u00e9veloppement de Taylor en \\(x_0\\). Si \\(p_n(x-x_0)\\to 0\\) lorsque \\(n\\to\\infty\\), alors \\(f\\) admet un\nd\u00e9veloppement de Taylor en \\(x_0\\). Si \\(p_n(x-x_0)\\to 0\\) lorsque \\(n\\to\\infty\\), alors \\(f\\) admet un\nd\u00e9veloppement de Taylor en \\(x_0\\). Si \\(p_n(x-x_0)\\to 0\\) lorsque \\(n\\to\\infty\\), alors \\(f\\) admet un\nd\u00e9veloppement de Taylor en \\(x_0\\). Si \\(p_n(x-x_0)\\to 0\\) lorsque \\(n\\to\\infty\\), alors \\(f\\) admet un\nd\u00e9veloppement de Taylor en \\(x_0\\). Si \\(p_n(x-x_0)\\to 0\\) lorsque \\(n\\to\\infty\\), alors \\(f\\) admet un\nd\u00e9veloppement de Taylor en \\(x_0\\)."
    },
    {
        "guid": "cc24cdb8-3a06-4a93-9b94-aca69608ddb1",
        "model_answer": "Soit $V$ une espace euclidien.On note $( u| v)$ le produit scalaire de deux vecteurs $ u, v\\in V$  et la normeassoci\\'ee est $\\| u\\|=\\sqrt{( u, u)}$.  Montrer les affirmations suivantes.$( u| v) = \\frac{1}{4} \\left(\\| u+ v\\|^2 - \\| u- v\\|^2\\right)$pour tous $ u, v\\in V$.\n$\\sqrt{( u, u)} = \\frac{1}{4} \\left(\\| u+ v\\|^2 - \\| u- v\\|^2\\right)$ pour tous $ u, v\\in V$.\n$\\sqrt{( u, u)} = \\frac{1}{4} \\left(\\| u+ v\\|^2 - \\| u- v\\|^2\\right)$ pour tous $ u, v\\in V$.\n$\\sqrt{( u, u)} = \\frac{1}{4} \\left(\\| u+ v\\|^2 - \\| u- v\\|^2\\right)$ pour tous $ u, v\\in V$.\n$\\sqrt{( u, u)} = \\frac{1}{4} \\left(\\| u+ v\\|^2 - \\| u- v\\|^2\\right)$ pour tous $ u, v\\in V$.\n$\\sqrt{( u, u)} = \\frac{1}{4} \\left(\\| u+ v\\|^2 - \\| u- v\\|^2\\right)$ pour tous $ u, v\\in V$.\n$\\sqrt{( u, u)} = \\frac{1}{4} \\left(\\| u+"
    },
    {
        "guid": "703e2827-6fe4-4f64-99ba-d81016d141ff",
        "model_answer": "Vrai ou faux? \\(\\displaystyle\\limsup_{n\\to\\infty} (a_n+b_n)=\n\\bigl(\\limsup_{n\\to\\infty}a_n\\bigr)+\n\\bigl(\\limsup_{n\\to\\infty}b_n\\bigr)\\)\n \\(\\displaystyle\\limsup_{n\\to\\infty} (a_nb_n)\n=\\bigl(\\limsup_{n\\to\\infty}a_n\\bigr)\n\\bigl(\\limsup_{n\\to\\infty}b_n\\bigr)\\)\n\\(\\displaystyle\\limsup_{n\\to\\infty} (a_n+b_n)\n=\\bigl(\\limsup_{n\\to\\infty}a_n\\bigr)+\n\\bigl(\\limsup_{n\\to\\infty}b_n\\bigr)\\)\n\\(\\displaystyle\\limsup_{n\\to\\infty} (a_n+b_n)\n=\\bigl(\\limsup_{n\\to\\infty}a_n\\bigr)+\n\\bigl(\\limsup_{n\\to\\infty}b_n\\bigr)\\)\n\\(\\displaystyle\\limsup_{n\\to\\infty} (a_n+b_n)\n=\\bigl(\\limsup_{n\\to\\infty}a_n\\bigr)+\n\\bigl(\\limsup_{n\\to\\infty}b_n\\bigr)\\)\n\\(\\displaystyle\\limsup_{n\\to\\infty} (a_n+b_n)\n=\\bigl(\\limsup_{n\\to\\infty}a_n\\bigr)+\n\\bigl(\\limsup_{n\\to\\infty}b_n\\bigr)\\)\n\\(\\displaystyle\\limsup_{n\\to\\infty} ("
    },
    {
        "guid": "e384b432-93ad-4770-9d13-74fc984cff31",
        "model_answer": "At which point does the venture start to bring in money? cashflow positive point profit point success point breakeven point\n\nI'm trying to figure this out.\n\n```\n$(function() {\n                                                                                                                                                                                                                                                                                       "
    },
    {
        "guid": "de41310c-1119-420c-84f7-f391781a5f97",
        "model_answer": "Une s\u00e9quence de 8 lettres est compos\u00e9e de 3 fois la lettre A, 3 fois la lettre B, 1 fois la lettre C et 1 fois la lettre D. Le calcul de son entropie donne \\(H\\simeq1.811\\). Quel dictionnaire est le plus appropri\u00e9 pour encoder cette s\u00e9quence en binaire? \\(A \\to 11, B \\to 10, C \\to 01, D \\to 00\\). \\(A \\to 0, B \\to 10, C \\to 11, D \\to 101\\). \\(A \\to 1, B \\to 01, C \\to 001, D \\to 000\\). \\(A \\to 1, B \\to 01, C \\to 001, D \\to 0001\\). \\(A \\to 1, B \\to 01, C \\to 001, D \\to 0001\\). \\(A \\to 1, B \\to 01, C \\to 001, D \\to 0001\\). \\(A \\to 1, B \\to 01, C \\to 001, D \\to 0001\\). \\(A \\to 1, B \\to 01, C \\to 001, D \\to 0001\\). \\(A \\to 1, B \\to 01, C \\to 001, D \\to 0001\\). \\(A \\to 1, B \\to 01, C \\to 001, D \\to 0001\\). \\(A \\to 1, B \\to 01, C \\to 001, D \\to 0001\\). \\(A \\to 1, B \\to 01, C \\to 001, D \\to 0001\\). \\(A \\to 1, B \\to 01, C \\to 001, D \\to 0001\\). \\(A \\to 1, B \\to 01, C \\to 001, D \\to 0001\\). \\(A \\to 1, B \\to 01, C \\to 001, D \\to 0001\\). \\(A \\to 1, B \\to 01, C \\to 001, D \\to 0001\\). \\(A \\to 1, B \\to 01, C"
    },
    {
        "guid": "68e15f77-d5da-484b-ba19-659cc1bea2da",
        "model_answer": "Why stars ionize the interstellar medium? It is the star's magnetic field that ejects electrons. Energy of the emitted photons is sufficiently high to dissociate atoms, and so to ionize them. Gravitational influence if sufficient to ionize the gas. The stellar wind particles have higher energy than the ionization energy of the gas.\n\n[asy]\nunitsize(1 cm);\n\npair A,B,C,D,E,F,G,H,I,J,K,L,M,N,O,P,Q,R,S,T,U,V,W,X,Y,Z;\n\nA = (0,0);\nB = (1,0);\nC = (2,0);\nD = (3,0);\nE = (4,0);\nF = (5,0);\nG = (6,0);\nH = (7,0);\nI = (8,0);\nJ = (9,0);\nK = (10,0);\nL = (11,0);\nM = (12,0);\nN = (13,0);\nO = (14,0);\nP = (15,0);\nQ = (16,0);\nR = (17,0);\nS = (18,0);\nT = (19,0);\nU = (20,0);\nV = (21,0);\nW = (22,0);\nX = (23,0);\nY = (24,0);\nZ = (25,0);\n\ndraw(A--B--C--D--E--F--G--H--I--J--"
    },
    {
        "guid": "bee98e82-357d-4d86-8c63-2f4c36b56e3f",
        "model_answer": "Assume that you are part of a team developing a mobile app using Scrum. One of your colleagues suggests that your team should organize daily Scrum meetings to discuss the progress of the tasks and how to implement complex features. He especially wants to discuss the implementation of a feature that will allow users to scan a QR code to get a discount, and would like some input from the team. What are your thoughts on this?\n\n* * * * * * * * * * * * * * * * * * * * * * * * * * * * * * * * * * * * * * * * * * * * * * * * * * * * * * * * * * * * * * * * * * * * * * * * * * * * * * * * * * * * * * * * * * * * * * * * * * * * * * * * * * * * * * * * * * * * * * * * * * * * * * * * * * * * * * * * * * * * * * * * * * * * * * * * * * * * * * * * * * * * * * * * * * * * * * * * * * * * * * * * * * * * * * * * * * * * * * * * * * * * * * * * * * * * * * * * * * * * * * * * * * * * * * * * * * * * * * * * * * * * * * * * * * * * * * * * * * * * * * * * * * * * * * * * * * * * * * * * * * * * * * * * * * * * * * * * * *"
    },
    {
        "guid": "19a6f5aa-151f-4b61-9cc2-5b2872ce4e6f",
        "model_answer": "Which statement about genetic metaheuristic optimization algorithms is true? The algorithms find the optimal parameter values over the whole possible parameter space It generates sets of parameter values (genotypes) that are used to generate and evaluate the resulting neuronal phenotype It generates a large number of random sets of parameter values that are ranked according to goodness of fit, the best fitting one is selected as the final set The algorithm uses several steps and generates new sets of parameters based on the best ranking set of the previous step The algorithm uses several steps and generates new sets of parameters based on the best ranking set of the previous step The algorithm uses several steps and generates new sets of parameters based on the best ranking set of the previous step The algorithm uses several steps and generates new sets of parameters based on the best ranking set of the previous step The algorithm uses several steps and generates new sets of parameters based on the best ranking set of the previous step The algorithm uses several steps and generates new sets of parameters based on the best ranking set of the previous step The algorithm uses several steps and generates new sets of parameters based on the best ranking set of the previous step The algorithm uses several steps and generates new sets of parameters based on the best ranking set of the previous step The algorithm uses several steps and generates new sets of parameters based on the best ranking set of the previous step The algorithm uses several steps and generates new sets of parameters based on the best ranking set of the previous step The algorithm uses several steps and generates new sets of parameters based on the best ranking set of the previous step The algorithm uses several steps and generates new sets of parameters based on the best ranking set of the previous step The algorithm uses several steps and generates new sets of parameters based on the best ranking set of the previous step The algorithm uses several steps and generates new sets of parameters based on the best ranking set of the previous step The algorithm uses several steps and generates new sets of parameters based on the best ranking set of the previous step The algorithm uses several steps and"
    },
    {
        "guid": "f61d34e0-d7a9-40f6-a9d1-02ca34b8dc3f",
        "model_answer": "Which of the following factors decreases contrast resolution? Smaller field of view Smaller matrix size Smaller voxel size Higher mAspectRatio Higher mAspectRatio Higher mAspectRatio Higher mAspectRatio Higher mAspectRatio Higher mAspectRatio Higher mAspectRatio Higher mAspectRatio Higher mAspectRatio Higher mAspectRatio Higher mAspectRatio Higher mAspectRatio Higher mAspectRatio Higher mAspectRatio Higher mAspectRatio Higher mAspectRatio Higher mAspectRatio Higher mAspectRatio Higher mAspectRatio Higher mAspectRatio Higher mAspectRatio Higher mAspectRatio Higher mAspectRatio Higher mAspectRatio Higher mAspectRatio Higher mAspectRatio Higher mAspectRatio Higher mAspectRatio Higher mAspectRatio Higher mAspectRatio Higher mAspectRatio Higher mAspectRatio Higher mAspectRatio Higher mAspectRatio Higher mAspectRatio Higher mAspectRatio Higher mAspectRatio Higher mAspectRatio Higher mAspectRatio Higher mAspectRatio Higher mAspectRatio Higher mAspectRatio Higher mAspectRatio Higher mAspectRatio Higher mAspectRatio Higher mAspectRatio Higher mAspectRatio Higher mAspectRatio Higher mAspectRatio Higher mAspectRatio Higher mAs"
    },
    {
        "guid": "83ae18dc-a016-4f97-adc4-402ac56b1359",
        "model_answer": "Why is simulation neuroscience needed? To bypass the measurement of all elements involved in the brain for all ages, species, strains and diseases To understand how all elements of the brain interact with each other\u2019s To predict what is the result of a change in some of the components composing the brain All of the above.\n\nWhy is simulation neuroscience needed? To bypass the measurement of all elements involved in the brain for all ages, species, strains and diseases To understand how all elements of the brain interact with each other\u2019s To predict what is the result of a change in some of the components composing the brain All of the above.\n\nWhat is the difference between simulation and neuroimaging?\n\nSimulation is a type of imaging that uses computer simulations to study brain function. It is used to study the structure and function of the brain. Neuroimaging is a type of imaging that uses magnetic resonance imaging (MRI) to study brain function. It is used to study the structure and function of the brain.\n\nWhat is the difference between simulation and neuroimaging?\n\nSimulation is a type of imaging that uses computer simulations to study brain function. It is used to study the structure and function of the brain. Neuroimaging is a type of imaging that uses magnetic resonance imaging (MRI) to study brain function. It is used to study the structure and function of the brain.\n\nWhat is the difference between simulation and neuroimaging?\n\nSimulation is a type of imaging that uses computer simulations to study brain function. It is used to study the structure and function of the brain. Neuroimaging is a type of imaging that uses magnetic resonance imaging (MRI) to study brain function. It is used to study the structure and function of the brain."
    },
    {
        "guid": "d875b0d6-054c-42b3-848f-7d354a32eea6",
        "model_answer": "What ion supports the fast-early inward current? A combination of chloride and calcium ions Sodium ions Potassium ions A combination of sodium and potassium ions\n\n[asy]\nunitsize(1 cm);\n\npair A,B,C,D,E,F,G,H,I,J,K,L,M,N,O,P,Q,R,S,T,U,V,W,X,Y,Z;\n\nA = (0,0);\nB = (1,0);\nC = (2,0);\nD = (3,0);\nE = (4,0);\nF = (5,0);\nG = (6,0);\nH = (7,0);\nI = (8,0);\nJ = (9,0);\nK = (10,0);\nL = (11,0);\nM = (12,0);\nN = (13,0);\nO = (14,0);\nP = (15,0);\nQ = (16,0);\nR = (17,0);\nS = (18,0);\nT = (19,0);\nU = (20,0);\nV = (21,0);\nW = (22,0);\nX = (23,0);\nY = (24,0);\nZ = (25,0);\n\ndraw(A--B--C--D--E--F--G--H--I--J--"
    },
    {
        "guid": "be73736f-6104-4dc5-b315-618c35f0e5f6",
        "model_answer": "Soit \\(f\\) d\u00e9rivable en \\(x_0\\), dont la d\u00e9riv\u00e9e est not\u00e9e \\(f'(x_0)\\). Alors le nombre \\(f(x_0)\\) est bien d\u00e9fini \\(\\displaystyle \\lim_{h\\to 0}\\frac{f(x_0)-f(x_0-h)}{h}=f'(x_0)\\) \\(\\displaystyle \\lim_{h\\to 0}\\frac{f(2x_0+h)-f(2x_0)}{h}=2f'(x_0)\\) \\(\\displaystyle \\lim_{z\\to x_0}\\frac{f(z)-f(x_0)}{z-x_0}=f'(x_0)\\) \\(\\displaystyle \\lim_{h\\to 0}\\frac{f(x_0+h^2)-f(x_0)}{h}=0\\)\n \\(\\displaystyle \\lim_{h\\to 0}\\frac{f(x_0+h)^2-f(x_0)^2}{h}=f'(x_0)^2\\)\n\\(\\displaystyle \\lim_{z\\to x_0}\\frac{f(z)-f(x_0)}{z-x_0}=f'(x_0)^2\\)\n\\(\\displaystyle \\lim_{h\\to 0}\\frac{f(x_0+h)^2-f(x_0)^2}{h}=f'(x_0)^2\\)\n\\(\\displaystyle \\lim_{h\\to 0}\\frac{f(x_0+h)^2-f(x_0)^2}{h}=f'(x_0)^2\\)\n\\(\\displaystyle \\lim_{h\\to 0}\\frac{f(x_0+h)^2-f(x_0)^2}{h}=f'(x_0)^2\\)\n\\(\\displaystyle \\lim_{h\\to 0}\\frac{f(x_0+h)^2-f(x_0)^2}{h}=f'(x_0)^2\\)\n\\(\\displaystyle \\lim_{h\\to 0}\\frac{f(x_0+h)^2-f(x_0)^2}{h}=f'(x_0)^2\\)\n\\(\\displaystyle \\lim_{h\\to 0}\\frac{"
    },
    {
        "guid": "1718610f-8dd6-4625-a6fb-becaf0881858",
        "model_answer": "What effect on chemical shift artefacts is created by an increased bandwidth? Worsens chemical shift artifacts Improves signal misregistration but not destructive interference (phase cancellation) Improves signal misregistration and destructive interference (phase cancellation) Worsens signal misregistration but does not affect destructive interference No effect on chemical shift artifact Worsens signal misregistration but does not affect destructive interference No effect on signal misregistration No effect on signal misregistration No effect on signal misregistration No effect on signal misregistration No effect on signal misregistration No effect on signal misregistration No effect on signal misregistration No effect on signal misregistration No effect on signal misregistration No effect on signal misregistration No effect on signal misregistration No effect on signal misregistration No effect on signal misregistration No effect on signal misregistration No effect on signal misregistration No effect on signal misregistration No effect on signal misregistration No effect on signal misregistration No effect on signal misregistration No effect on signal misregistration No effect on signal misregistration No effect on signal misregistration No effect on signal misregistration No effect on signal misregistration No effect on signal misregistration No effect on signal misregistration No effect on signal misregistration No effect on signal misregistration No effect on signal misregistration No effect on signal misregistration No effect on signal misregistration No effect on signal misregistration No effect on signal misregistration No effect on signal misregistration No effect on signal misregistration No effect on signal misregistration No effect on signal misregistration No effect on signal misregistration No effect on signal misregistration No effect on signal misregistration No effect on signal misregistration"
    },
    {
        "guid": "8bd54ea2-2ebb-40d4-9450-7b14a8b06b8a",
        "model_answer": "(c) Define total current [mathjaxinline]j_{tot}=j_{grav}+j_D[/mathjaxinline], find the steady state solution for [mathjaxinline]j_{tot}[/mathjaxinline] and derive the diffusion constant D. This corresponds to Einstein\u2019s derivation. [mathjaxinline]D=\\frac{m g}{k_{B} T}[/mathjaxinline] [mathjaxinline]D=\\frac{m \\gamma}{k_{B} T}[/mathjaxinline] [mathjaxinline]D=\\frac{k_{B} T}{m g}[/mathjaxinline] [mathjaxinline]D=\\frac{k_{B} T}{m \\gamma}[/mathjaxinline] [mathjaxinline]D=\\frac{k_{B} T}{m \\gamma}[/mathjaxinline] [mathjaxinline]D=\\frac{k_{B} T}{m \\gamma}[/mathjaxinline] [mathjaxinline]D=\\frac{k_{B} T}{m \\gamma}[/mathjaxinline] [mathjaxinline]D=\\frac{k_{B} T}{m \\gamma}[/mathjaxinline] [mathjaxinline]D=\\frac{k_{B} T}{m \\gamma}[/mathjaxinline] [mathjaxinline]D=\\frac{k_{B} T}{m \\gamma}[/mathjaxinline] [mathjaxinline]D=\\frac{k_{B} T}{m \\gamma}[/mathjaxinline] [mathjaxinline]D=\\frac{k_{B} T}{m \\gamma}[/mathjaxinline] [mathjaxinline]D=\\frac{k_{B} T}{m \\gamma}[/mathjaxinline] [mathjaxinline]D=\\frac{k_{B} T}{m \\gamma}[/mathjaxinline] [mathjaxinline]D=\\frac{k_{B} T}{m \\gam"
    },
    {
        "guid": "70f8efa0-1816-445b-a053-cf92ee323bab",
        "model_answer": "Natural frequency of precession and Larmor frequency are... Different names for the same frequency Two different frequencies of precession and Larmor frequency Two different frequencies of precession and Larmor frequency Two different frequencies of precession and Larmor frequency Two different frequencies of precession and Larmor frequency Two different frequencies of precession and Larmor frequency Two different frequencies of precession and Larmor frequency Two different frequencies of precession and Larmor frequency Two different frequencies of precession and Larmor frequency Two different frequencies of precession and Larmor frequency Two different frequencies of precession and Larmor frequency Two different frequencies of precession and Larmor frequency Two different frequencies of precession and Larmor frequency Two different frequencies of precession and Larmor frequency Two different frequencies of precession and Larmor frequency Two different frequencies of precession and Larmor frequency Two different frequencies of precession and Larmor frequency Two different frequencies of precession and Larmor frequency Two different frequencies of precession and Larmor frequency Two different frequencies of precession and Larmor frequency Two different frequencies of precession and Larmor frequency Two different frequencies of precession and Larmor frequency Two different frequencies of precession and Larmor frequency Two different frequencies of precession and Larmor frequency Two different frequencies of precession and Larmor frequency Two different frequencies of precession and Larmor frequency Two different frequencies of precession and Larmor frequency Two different frequencies of precession and Larmor frequency Two different frequencies of precession and Larmor frequency Two different frequencies of precession and Larmor frequency Two different frequencies of precession and Larmor frequency Two different frequencies"
    },
    {
        "guid": "e35d196d-d378-4134-9ac5-2e799a393890",
        "model_answer": "Calculez la matrice associ\\'ee \\`a laprojection orthogonale sur le plan \\(W\\) de \\(\\mathbb{R}^3\\) donn\\'e par\\[ W=\\left\\{\\vec{x}=\\left.\\begin{pmatrix}x_1\\\\ x_2\\\\x_3\\end{pmatrix}\\right| 2x_1-x_2=0\\right\\}\\,.\\]Ainsi que la matrice associ\\'ee \\`a laprojection orthogonale sur le plan \\(W\\) de \\(\\mathbb{R}^3\\) donn\\'e par\\[ W=\\left\\{\\vec{x}=\\left.\\begin{pmatrix}x_1\\\\ x_2\\\\x_3\\end{pmatrix}\\right| 2x_1-x_2=0\\right\\}\\,.\\]Ainsi que la matrice associ\\'ee \\`a laprojection orthogonale sur le plan \\(W\\) de \\(\\mathbb{R}^3\\) donn\\'e par\\[ W=\\left\\{\\vec{x}=\\left.\\begin{pmatrix}x_1\\\\ x_2\\\\x_3\\end{pmatrix}\\right| 2x_1-x_2=0\\right\\}\\,.\\]Ainsi que la matrice associ\\'ee \\`a laprojection orthogonale sur le plan \\(W\\) de \\(\\mathbb{R}^3\\) donn\\'e par\\[ W=\\left\\{\\vec{x}=\\left.\\begin{pmatrix}x_1\\\\ x_2\\\\x_3\\end{pmatrix}\\right| 2x_1-x_2=0\\right\\}\\"
    },
    {
        "guid": "edc67f0d-3970-4202-88be-01a9fdc54246",
        "model_answer": "Assume that the patterns [mathjaxinline] p^{\\mu} [/mathjaxinline] have the property [mathjaxinline] \\sum_{i=1}^N p_i^{\\mu} = 0 ~~ \\forall \\mu[/mathjaxinline]. Which of the following interpretations of this property is correct: The patterns are balanced: The mean of each pixel across patterns is zero All pixels of all patterns are equal to zero. Half of the patterns only show positiv, the other half only negative pixels All patterns are balanced: Each pattern has the same number of active and inactive pixels. Each pattern has the same number of active and inactive pixels. Each pattern has the same number of active and inactive pixels. Each pattern has the same number of active and inactive pixels. Each pattern has the same number of active and inactive pixels. Each pattern has the same number of active and inactive pixels. Each pattern has the same number of active and inactive pixels. Each pattern has the same number of active and inactive pixels. Each pattern has the same number of active and inactive pixels. Each pattern has the same number of active and inactive pixels. Each pattern has the same number of active and inactive pixels. Each pattern has the same number of active and inactive pixels. Each pattern has the same number of active and inactive pixels. Each pattern has the same number of active and inactive pixels. Each pattern has the same number of active and inactive pixels. Each pattern has the same number of active and inactive pixels. Each pattern has the same number of active and inactive pixels. Each pattern has the same number of active and inactive pixels. Each pattern has the same number of active and inactive pixels. Each pattern has the same number of active and inactive pixels. Each pattern has the same number of active and inactive pixels. Each pattern has the same number of active and inactive pixels. Each pattern has the same number of active and inactive pixels. Each pattern has the same number of active and inactive pixels. Each pattern has the same number of active and inactive pixels. Each pattern has the same number of active and inactive pixels."
    },
    {
        "guid": "3b7e8491-0a75-4620-9a08-5236121d55a3",
        "model_answer": "We will analyze the $K$-means algorithm and show that it always converge. Let us consider the $K$-means objective function: $$ \\mathcal{L}(\\mathbf{z}, \\boldsymbol{\\mu})=\\sum_{n=1}^{N} \\sum_{k=1}^{K} z_{n k}\\left\\|\\mathbf{x}_{n}-\\boldsymbol{\\mu}_{k}\\right\\|_{2}^{2} $$ where $z_{n k} \\in\\{0,1\\}$ with $\\sum_{k=1}^{K} z_{n k}=1$ and $\\boldsymbol{\\mu}_{k} \\in \\mathbb{R}^{D}$ for $k=1, \\ldots, K$ and $n=1, \\ldots, N$. How would you choose $\\left\\{\\boldsymbol{\\mu}_{k}\\right\\}_{k=1}^{K}$ to minimize $\\mathcal{L}(\\mathbf{z}, \\boldsymbol{\\mu})$ for given $\\left\\{z_{n k}\\right\\}_{n, k=1}^{N, K}$? Compute the closed-form formula for the $\\boldsymbol{\\mu}_{k}$. To which step of the $K$-means algorithm does it correspond? \n\n[asy]\nunitsize(1 cm);\n\npair A,B,C,D,E,F,G,H,I,J,K,L,M,N,O,P,Q,R,S,T,U,V,W,X,Y,Z;\nA = (0,0);\nB = (0,1);\nC = (0,2);\nD = (0,3);\nE = (0,4);\nF = (0,5);\nG = (0,6);\nH = (0,7);\nI = (0,8);\nJ = (0,9);\nK = (0,10);\nL = (0,11);\nM = (0,12);\nN = (0,13);\nO = (0,14);\nP = (0,15);\nQ = (0,16);\nR = (0,17);\nS = (0,18);\nT = (0,19);\nU = (0,20);\nV = (0,21);\nW = (0,22);\nX = (0,23);\nY = (0,24);\nZ = (0,25);\ndraw(A--B--C--D--E--F--G--H--I--J--K--"
    },
    {
        "guid": "53d7b649-afab-48bd-a2b4-769df94b491c",
        "model_answer": "How long does it take for the free induction decay of an NMR line with T2 = 0.5 s to decay to 1% of its initial amplitude? 2.30 s 2.90 s 3.20 s 3.70 s 4.00 s 4.30 s 5.00 s 5.30 s 6.00 s 6.30 s 7.00 s 7.30 s 8.00 s 8.30 s 9.00 s 9.30 s 10.00 s 10.30 s 11.00 s 11.30 s 12.00 s 12.30 s 13.00 s 13.30 s 14.00 s 14.30 s 15.00 s 15.30 s 16.00 s 16.30 s 17.00 s 17.30 s 18.00 s 18.30 s 19.00 s 19.30 s 20.00 s 20.30 s 21.00 s 21.30 s 22.00 s 22.30 s 23.00 s 23.30 s 24.00 s 24.30 s 25.00 s 25.30 s 26.00 s 26.30 s 27.00 s 27.30 s 28.00 s 28.30 s 29.00 s 29.30 s 30.00 s 30.30 s 31.00 s 31.30 s 32.00 s 32.30 s 33.00 s 33.30 s 34.00 s 34.30 s 35.00 s 35.30 s 36.00 s 36.30 s 37.00 s 37.30 s 38.00 s 38.30 s 39.00 s 39.30 s 40.00 s 40.30 s 41.00 s"
    },
    {
        "guid": "245c93a8-3253-4b95-aca5-6918cf5bd650",
        "model_answer": "Quel est un des avantages d'un syst\u00e8me r\u00e9luctant polaris\u00e9? (une seule r\u00e9ponse possible) la force est proportionnelle au courant la structure simple le positionnement de la pi\u00e8ce mobile se fait sans alimentation l'inertie est faible.\n\nAinsi, cela n'est pas possible que cela n'est pas possible que cela n'est pas possible que cela n'est pas possible que cela n'est pas possible que cela n'est pas possible que cela n'est pas possible que cela n'est pas possible que cela n'est pas possible que cela n'est pas possible que cela n'est pas possible que cela n'est pas possible que cela n'est pas possible que cela n'est pas possible que cela n'est pas possible que cela n'est pas possible que cela n'est pas possible que cela n'est pas possible que cela n'est pas possible que cela n'est pas possible que cela n'est pas possible que cela n'est pas possible que cela n'est pas possible que cela n'est pas possible que cela n'est pas possible que cela n'est pas possible que cela n'est pas possible que cela n'est pas possible que cela n'est pas possible que cela n'est pas possible que cela n'est pas possible que cela n'est pas possible que cela n'est pas possible que cela n'est pas possible que cela n'est pas possible que cela n'est pas possible que cela n'est"
    },
    {
        "guid": "bfef8387-5cd3-4cb1-9fbe-ae87f876425a",
        "model_answer": "Which smart tricks did Hodgkin and Huxley use to measure the underlying mechanisms that enable the spikes? A current clamp keeping the current running in the axon constant A space clamp that renders the full axon iso-potential A voltage clamp to force the two side of the membrane to have a fixes voltage difference A conductance clamp to fix the current passing through the membrane A voltage clamp to force the two side of the membrane to have a fixes voltage difference\n\n[asy]\nsize(150);\n\npair A,B,C,D,E,F,G,H,I,J,K,L,M,N,O,P,Q,R,S,T,U,V,W,X,Y,Z,A,B,C,D,E,F,G,H,I,J,K,L,M,N,O,P,Q,R,S,T,U,V,W,X,Y,Z,A,B,C,D,E,F,G,H,I,J,K,L,M,N,O,P,Q,R,S,T,U,V,W,X,Y,Z,A,B,C,D,E,F,G,H,I,J,K,L,M,N,O,P,Q,R,S,T,U,V,W,X,Y,Z,A,B,C,D,E,F,G,H,I,J,K,L,M,N,O,P,Q,R,S,T,U,V,W,X,Y,Z,A,B,C,D,E,"
    },
    {
        "guid": "13739c83-35d1-4fec-867c-98bd69f9ae73",
        "model_answer": "You are doing your ML project. It is a regression task under a square loss. Your neighbor uses linear regression and least squares. You are smarter. You are using a neural net with 10 layers and activations functions $f(x)=3 x$. You have a powerful laptop but not a supercomputer. You are betting your neighbor a beer at Satellite who will have a substantially better scores. However, at the end it will essentially be a tie, so we decide to have two beers and both pay. What is the reason for the outcome of this bet? Because we use exactly the same scheme. Because it is almost impossible to train a network with 10 layers without a supercomputer. Because I should have used more layers. Because I should have used only one layer.\n\nIf you want to know more about neural nets, check out this article:\n\nhttp://arxiv.org/abs/1612.06522\n\nIf you want to know more about neural nets, check out this article:\n\nhttp://arxiv.org/abs/1612.06522\n\nIf you want to know more about neural nets, check out this article:\n\nhttp://arxiv.org/abs/1612.06522\n\nIf you want to know more about neural nets, check out this article:\n\nhttp://arxiv.org/abs/1612.06522\n\nIf you want to know more about neural nets, check out this article:\n\nhttp://arxiv.org/abs/1612.06522\n\nIf you want to know more about neural nets, check out this article:\n\nhttp://arxiv.org/abs/1612.06522\n\nIf you want to know more about neural nets, check out this article:\n\nhttp://arxiv.org/abs/1612.06522\n\nIf you want to know more about neural nets, check out this article:\n\nhttp://arxiv.org/abs/1612.06522\n\nIf you want to know more about neural nets, check out this article:\n\nhttp"
    },
    {
        "guid": "64a34fa8-6bda-475f-b7da-b752ff1d1456",
        "model_answer": "Que dit la loi d'Ohm g\u00e9n\u00e9ralis\u00e9e \u00e0 propos de la tension au bornes d'une bobine travers\u00e9e par un courant? (une seule r\u00e9ponse possible) rien qu'elle est \u00e9gale \u00e0 la r\u00e9sistance du fil multipli\u00e9 par le courant qu'elle est \u00e9gale \u00e0 la r\u00e9sistance du fil multipli\u00e9 par le courant, plus la variation du flux totalis\u00e9 qu'elle est \u00e9gale \u00e0 la r\u00e9sistance du fil multipli\u00e9 par le courant, mois la variation du flux totalis\u00e9 qu'elle est \u00e9gale \u00e0 la r\u00e9sistance du fil multipli\u00e9 par le courant, plus la variation du flux totalis\u00e9 qu'elle est \u00e9gale \u00e0 la r\u00e9sistance du fil multipli\u00e9 par le courant, plus la variation du flux totalis\u00e9 qu'elle est \u00e9gale \u00e0 la r\u00e9sistance du fil multipli\u00e9 par le courant, plus la variation du flux totalis\u00e9 qu'elle est \u00e9gale \u00e0 la r\u00e9sistance du fil multipli\u00e9 par le courant, plus la variation du flux totalis\u00e9 qu'elle est \u00e9gale \u00e0 la r\u00e9sistance du fil multipli\u00e9 par le courant, plus la variation du flux totalis\u00e9 qu'elle est \u00e9gale \u00e0 la r\u00e9sistance du fil multipli\u00e9 par le courant, plus la variation du flux totalis\u00e9 qu'elle est \u00e9gale \u00e0 la r\u00e9sistance du fil multipli\u00e9 par le courant, plus la variation du flux totalis\u00e9 qu'elle est \u00e9gale \u00e0 la r\u00e9sistance du fil multipli\u00e9 par le courant, plus la variation du flux totalis\u00e9 qu'elle est \u00e9gale \u00e0 la r\u00e9sistance du fil multipli\u00e9 par le courant, plus la variation du flux totalis\u00e9 qu'elle est \u00e9gale \u00e0 la r\u00e9sistance du fil multipli\u00e9 par le courant, plus la variation du flux totalis\u00e9"
    },
    {
        "guid": "e88dde48-5fbb-46b6-855f-1b41da17322b",
        "model_answer": "How does human postnatal brain development compare to mouse postnatal brain development? They are the same Mice are born with a more mature brain than humans, thus less happen during their postnatal development Humans are born with a more mature brain, thus parts of mouse postnatal development correspond to human embryonic development There is no postnatal brain development in humans.\n\nHuman postnatal brain development is similar to mouse postnatal brain development. There is no postnatal brain development in humans.\n\nHuman postnatal brain development is similar to mouse postnatal brain development. There is no postnatal brain development in humans.\n\nHuman postnatal brain development is similar to mouse postnatal brain development. There is no postnatal brain development in humans.\n\nHuman postnatal brain development is similar to mouse postnatal brain development. There is no postnatal brain development in humans.\n\nHuman postnatal brain development is similar to mouse postnatal brain development. There is no postnatal brain development in humans.\n\nHuman postnatal brain development is similar to mouse postnatal brain development. There is no postnatal brain development in humans.\n\nHuman postnatal brain development is similar to mouse postnatal brain development. There is no postnatal brain development in humans.\n\nHuman postnatal brain development is similar to mouse postnatal brain development. There is no postnatal brain development in humans.\n\nHuman postnatal brain development is similar to mouse postnatal brain development. There is no postnatal brain development in humans.\n\nHuman postnatal brain development is similar to mouse postnatal brain development. There is no postnatal brain development in humans.\n\nHuman postnatal brain development is similar to mouse postnatal brain development. There is no postnatal brain development in humans.\n\nHuman postnatal brain development is similar to mouse postnatal"
    },
    {
        "guid": "c3842176-bc8b-4bba-8ad5-fb127d3282d8",
        "model_answer": "Mark the true statements. (a)  Logistic loss is typically preferred over $L_{2}$ loss (least squares loss) in classification tasks. (b)  In terms of feature selection, $L_{2}$ regularization is often preferred since it comes up with sparse solutions. (c)  In terms of feature selection, $L_{2}$ regularization is often preferred over $L_{1}$ regularization. (d)  In terms of feature selection, $L_{2}$ regularization is often preferred over $L_{1}$ regularization. (e)  In terms of feature selection, $L_{2}$ regularization is often preferred over $L_{1}$ regularization. (f)  In terms of feature selection, $L_{2}$ regularization is often preferred over $L_{1}$ regularization. (g)  In terms of feature selection, $L_{2}$ regularization is often preferred over $L_{1}$ regularization. (h)  In terms of feature selection, $L_{2}$ regularization is often preferred over $L_{1}$ regularization. (i)  In terms of feature selection, $L_{2}$ regularization is often preferred over $L_{1}$ regularization. (j)  In terms of feature selection, $L_{2}$ regularization is often preferred over $L_{1}$ regularization. (k)  In terms of feature selection, $L_{2}$ regularization is often preferred over $L_{1}$ regularization. (l)  In terms of feature selection, $L_{2}$ regularization is often preferred"
    },
    {
        "guid": "d32e91ed-7eb4-44cd-be2b-2defaff5ce00",
        "model_answer": "How are somatic and dendritic conductances related to the firing pattern of a cell? Each cell type has a fixed firing pattern that results from all individual cells of the same type having the same somatic and dendritic conductances Each combination of conductances generate a different firing behavior Specific conductances must be at certain levels in order to generating a defined firing pattern Several combinations of conductances are able to reproduce the same firing behavior in different cell types Different combinations of conductances are able to reproduce the same firing behavior in different cell types Different combinations of conductances are able to reproduce the same firing behavior in different cell types Different combinations of conductances are able to reproduce the same firing behavior in different cell types Different combinations of conductances are able to reproduce the same firing behavior in different cell types Different combinations of conductances are able to reproduce the same firing behavior in different cell types Different combinations of conductances are able to reproduce the same firing behavior in different cell types Different combinations of conductances are able to reproduce the same firing behavior in different cell types Different combinations of conductances are able to reproduce the same firing behavior in different cell types Different combinations of conductances are able to reproduce the same firing behavior in different cell types Different combinations of conductances are able to reproduce the same firing behavior in different cell types Different combinations of conductances are able to reproduce the same firing behavior in different cell types Different combinations of conductances are able to reproduce the same firing behavior in different cell types Different combinations of conductances are able to reproduce the same firing behavior in different cell types Different combinations of conductances are able to reproduce the same firing behavior in different cell types Different combinations of conductances are able to reproduce the same firing behavior in different cell types Different combinations of conductances are able to reproduce the same firing behavior in different cell types Different combinations of conductances are able to reproduce the same firing behavior in different cell types Different combinations of conductances are able"
    },
    {
        "guid": "24e3fd38-37a4-4934-b74d-dc666e8c60b8",
        "model_answer": "Which of the following statements is NOT correct: GABAergic neurons make synapses at specific dendritic locations GABA acts upon postsynaptic neurons to prevent them from firing action potentials GABAergic inhibition counteracts glutamatergic excitation in neuronal networks of the brain Most neurons in the brain are GABAergic in order to maintain the balance between excitation and inhibiton, and GABAergic neurons make synapses at specific dendritic locations GABA acts upon postsynaptic neurons to prevent them from firing action potentials GABAergic inhibition counteracts glutamatergic excitation in neuronal networks of the brain Most neurons in the brain are GABAergic in order to maintain the balance between excitation and inhibiton, and GABAergic neurons make synapses at specific dendritic locations GABA acts upon postsynaptic neurons to prevent them from firing action potentials GABAergic inhibition counteracts glutamatergic excitation in neuronal networks of the brain Most neurons in the brain are GABAergic in order to maintain the balance between excitation and inhibiton, and GABAergic neurons make synapses at specific dendritic locations GABA acts upon postsynaptic neurons to prevent them from firing action potentials GABAergic inhibition counteracts glutamatergic excitation in neuronal networks of the brain Most neurons in the brain are GABAergic in order to maintain the balance between excitation and inhibiton, and GABAergic neurons make synapses at specific dendritic locations GABA acts upon postsynaptic neurons to prevent them from firing action potentials GABAergic inhibition counteracts glutamatergic excitation in neuronal networks of the brain Most neurons in the brain are GABAergic in order to maintain the balance between excitation and inhibiton, and GABAergic neurons make synapses at specific dendritic locations GABA acts upon postsynaptic neurons to prevent them from firing action potentials GABAergic inhibition"
    },
    {
        "guid": "056ea0f5-990e-45ec-9d81-60ec66ecf9a9",
        "model_answer": "Expand the right-hand side of the recursion relation of p(n\u0394,(k+1)\u03c4). Divide the equation by time increment \u03c4 and take the limit \u03c4\u21920,choose the correct diffusion equation: [mathjaxinline]\\frac{\\partial p(n \\Delta, k \\tau)}{\\partial t}=\\frac{\\Delta^{2}}{\\tau} \\frac{\\partial^{2}}{\\partial x^{2}} p(n \\Delta, k \\tau)[/mathjaxinline] [mathjaxinline]\\frac{\\partial p(n \\Delta, k \\tau)}{\\partial t}=\\frac{\\Delta^{2}}{ \\tau} \\frac{\\partial^{2}}{\\partial x^{2}} p(n \\Delta, k \\tau)+\\frac{(q-p) \\cdot \\Delta}{\\tau} \\cdot \\frac{\\partial}{\\partial x} p(n \\Delta, k \\tau)[/mathjaxinline] [mathjaxinline]\\frac{\\partial p(n \\Delta, k \\tau)}{\\partial t}=\\frac{\\Delta^{2}}{2 \\tau} \\frac{\\partial^{2}}{\\partial x^{2}} p(n \\Delta, k \\tau)[/mathjaxinline] [mathjaxinline]\\frac{\\partial p(n \\Delta, k \\tau)}{\\partial t}=\\frac{\\Delta^{2}}{2 \\tau} \\frac{\\partial^{2}}{\\partial x^{2}} p(n \\Delta, k \\tau)+\\frac{(q-p) \\cdot \\Delta}{\\tau} \\cdot \\frac{\\partial}{\\partial x} p(n \\Delta, k \\tau)[/mathjaxinline] [mathjaxinline]\\frac{\\partial p(n \\Delta, k \\tau)}{\\partial t}=\\frac{\\Delta^{2}}{2 \\tau} \\frac{\\partial^{2}}{\\partial x^{2}} p(n \\Delta, k \\tau)+\\frac{(q-p) \\cdot \\Delta}{\\tau} \\cdot \\frac{\\partial}{\\partial x} p(n \\Delta, k \\tau)[/mathjaxinline] [mathjaxinline]\\frac{\\partial p(n \\Delta, k \\tau)}{\\partial t}=\\frac{\\Delta^{2}}{2 \\tau} \\frac{\\partial^{2}}{\\partial x^{2}} p(n \\Delta, k \\tau)+\\frac{(q-p) \\cdot \\Delta}{\\tau} \\cdot \\frac{\\partial}{\\partial x} p(n \\Delta, k \\tau)[/mathjaxinline] [mathjaxinline]\\frac{\\partial p(n \\Delta, k \\tau)}{\\partial t}=\\frac{\\Delta^{2}}{2 \\tau} \\frac{\\partial^{2}}{\\partial x^{2}} p(n \\Delta, k \\tau)+\\frac{(q-p) \\cdot \\Delta}{"
    },
    {
        "guid": "2d9de929-7645-4192-8b90-8a7c253b162a",
        "model_answer": "Genome sequencing can provide information on... the potential genetic basis of diseases the causes of genetic mutations in the population the level of genetic diversity within a population the effect of genetic diversity on gene expression the impact of genetic diversity on the expression of genes the effect of genetic diversity on the expression of genes the effect of genetic diversity on the expression of genes the effect of genetic diversity on the expression of genes the effect of genetic diversity on the expression of genes the effect of genetic diversity on the expression of genes the effect of genetic diversity on the expression of genes the effect of genetic diversity on the expression of genes the effect of genetic diversity on the expression of genes the effect of genetic diversity on the expression of genes the effect of genetic diversity on the expression of genes the effect of genetic diversity on the expression of genes the effect of genetic diversity on the expression of genes the effect of genetic diversity on the expression of genes the effect of genetic diversity on the expression of genes the effect of genetic diversity on the expression of genes the effect of genetic diversity on the expression of genes the effect of genetic diversity on the expression of genes the effect of genetic diversity on the expression of genes the effect of genetic diversity on the expression of genes the effect of genetic diversity on the expression of genes the effect of genetic diversity on the expression of genes the effect of genetic diversity on the expression of genes the effect of genetic diversity on the expression of genes the effect of genetic diversity on the expression of genes the effect of genetic diversity on the expression of genes the effect of genetic diversity on the expression of genes the effect of genetic diversity on the expression of genes the effect of genetic diversity on the expression of genes the effect of genetic diversity on the expression of genes"
    },
    {
        "guid": "1d74cd2f-d3fc-4f0e-b3ec-b27225b9160e",
        "model_answer": "In JOS and x86, please select all valid options for a system call. A system call is for handling interrupts like dividing zero error and page fault. In user mode, before and after a system call instruction(such as int 0x30), the stack pointer(esp in x86) stays the same. During the execution of a system call, when transfering from user mode to kernel mode, the stack pointer(esp in x86) stays the same.\n\n```\nint i, j;\n\nfor (i = 0; i < 4; ++i)\n                                                                                                                                                                                                                                                                                  "
    },
    {
        "guid": "aa7e1cbf-f33f-4579-83d7-3bef5673a7ba",
        "model_answer": "Consider the case that the mechanical oscillator is coupled to the cavity bath. The laser is pumped red detuned from the cavity resonance by the mechanical frequency. What is the minimum phonon number in the resolved sideband limit (\\(\\Omega_m \u226b \\kappa\\))? \\(\\bigg(\\dfrac{\\kappa}{4\\Omega}\\bigg)^2\\) \\(\\dfrac{\\kappa}{4\\Omega}\\) \\(\\dfrac{4g^2}{\\kappa\\Gamma}\\) \\( \\dfrac{4 g}{\\kappa}\\) \\(\\bigg(\\dfrac{\\kappa}{4\\Omega}\\bigg)^2\\) \\(\\bigg(\\dfrac{\\kappa}{4\\Omega}\\) \\(\\bigg(\\dfrac{\\kappa}{4\\Omega}\\) \\(\\bigg(\\dfrac{\\kappa}{4\\Omega}\\) \\(\\bigg(\\dfrac{\\kappa}{4\\Omega}\\) \\(\\bigg(\\dfrac{\\kappa}{4\\Omega}\\) \\(\\bigg(\\dfrac{\\kappa}{4\\Omega}\\) \\(\\bigg(\\dfrac{\\kappa}{4\\Omega}\\) \\(\\bigg(\\dfrac{\\kappa}{4\\Omega}\\) \\(\\bigg(\\dfrac{\\kappa}{4\\Omega}\\) \\(\\bigg(\\dfrac{\\kappa}{4\\Omega}\\) \\(\\bigg(\\dfrac{\\kappa}{4\\Omega}\\) \\(\\bigg(\\dfrac{\\kappa}{4\\Omega}\\) \\(\\bigg(\\dfrac{\\kappa}{4\\Omega}\\) \\(\\bigg(\\dfrac{\\kappa}{4\\Omega}\\) \\(\\bigg(\\dfrac{\\kappa}{4\\Omega}\\) \\(\\bigg(\\dfrac{\\kappa}{4\\Omega}\\) \\(\\bigg(\\dfrac{\\kappa}{4\\Omega}\\) \\(\\bigg(\\dfrac{\\"
    },
    {
        "guid": "ee1a1937-ed58-499b-94ea-fe6fdd4717e2",
        "model_answer": "\"D\" est la lettre qui symbolise: le champ \u00e9lectrique le d\u00e9placement \u00e9lectrique le champ magn\u00e9tique le champ d'induction magn\u00e9tique la densit\u00e9 de courantes \u00e9lectromagn\u00e9tiques \u00e9lectromagn\u00e9tiques \u00e9lectromagn\u00e9tiques \u00e9lectromagn\u00e9tiques \u00e9lectromagn\u00e9tiques \u00e9lectromagn\u00e9tiques \u00e9lectromagn\u00e9tiques \u00e9lectromagn\u00e9tiques \u00e9lectromagn\u00e9tiques \u00e9lectromagn\u00e9tiques \u00e9lectromagn\u00e9tiques \u00e9lectromagn\u00e9tiques \u00e9lectromagn\u00e9tiques \u00e9lectromagn\u00e9tiques \u00e9lectromagn\u00e9tiques \u00e9lectromagn\u00e9tiques \u00e9lectromagn\u00e9tiques \u00e9lectromagn\u00e9tiques \u00e9lectromagn\u00e9tiques \u00e9lectromagn\u00e9tiques \u00e9lectromagn\u00e9tiques \u00e9lectromagn\u00e9tiques \u00e9lectromagn\u00e9tiques \u00e9lectromagn\u00e9tiques \u00e9lectromagn\u00e9tiques \u00e9lectromagn\u00e9tiques \u00e9lectromagn\u00e9tiques \u00e9lectromagn\u00e9tiques \u00e9lectromagn\u00e9tiques \u00e9lectromagn\u00e9tiques \u00e9lectromagn\u00e9tiques \u00e9lectromagn\u00e9tiques \u00e9lectromagn\u00e9tiques \u00e9lectromagn\u00e9tiques \u00e9lectromagn\u00e9tiques \u00e9lectromagn\u00e9tiques \u00e9lectromagn\u00e9tiques \u00e9lectromagn\u00e9tiques \u00e9lectromagn\u00e9tiques \u00e9lectromagn\u00e9tiques \u00e9lectromagn\u00e9tiques \u00e9lectromagn\u00e9tiques \u00e9lectromagn\u00e9tiques \u00e9lectromagn\u00e9tiques \u00e9lectromagn\u00e9tiques \u00e9lectromagn\u00e9tiques \u00e9lectromagn\u00e9tiques \u00e9lectromagn\u00e9tiques \u00e9lectromagn\u00e9tiques \u00e9lectromagn\u00e9t"
    },
    {
        "guid": "4c07c694-88e7-48d8-b711-e8809a0c679d",
        "model_answer": "What is the principle behind the polymerase chain reaction? One of the two DNA strands can be used as a template to translate DNA into RNA One of the two DNA strands can be used as a template to copy and amplify a DNA sequence The enzyme DNA polymerase emits different light signals when adding different nucleotides during DNA synthesis The enzyme DNA polymerase cleaves only T nucleotides, which is why it is called DNA polymerase\n\n[asy]\nsize(150);\n\npair A,B,C,D,E,F,G,H,I,J,K,L,M,N,O,P,Q,R,S,T,U,V,W,X,Y,Z;\nA = (0,0);\nB = (1,0);\nC = (2,0);\nD = (3,0);\nE = (4,0);\nF = (5,0);\nG = (6,0);\nH = (7,0);\nI = (8,0);\nJ = (9,0);\nK = (10,0);\nL = (11,0);\nM = (12,0);\nN = (13,0);\nO = (14,0);\nP = (15,0);\nQ = (16,0);\nR = (17,0);\nS = (18,0);\nT = (19,0);\nU = (20,0);\nV = (21,0);\nW = (22,0);\nX = (23,0);\nY = (24,0);\nZ = (25,0);\n\ndraw(A--B--C--D--E--F--G"
    },
    {
        "guid": "76ce9513-bd2e-460e-a0b4-7a36819646d2",
        "model_answer": "Soit \\(x\\) un r\u00e9el quelconque.\nVrai ou faux? Pour tout entier \\(n\\geq 1\\), il existe un\nrationnel \\(y\\) tel que \\(0\\lt |x-y|\\leq \\frac{1}{10^n}\\). Pour tout entier \\(n\\geq 1\\), il existe un\nirrationnel \\(y\\) tel que \\(0\\lt |x-y|\\leq \\frac{1}{10^n}\\). Pour tout entier \\(n\\geq 1\\), il existe une\ninfinit\u00e9 de rationnels \\(y\\) tels que \\(0\\lt |x-y|\\leq \\frac{1}{10^n}\\). Pour tout entier \\(n\\geq 1\\), il existe une infinit\u00e9 \nd'irrationnels \\(y\\) tels que \\(0\\lt |x-y|\\leq \\frac{1}{10^n}\\). Pour tout entier \\(n\\geq 1\\), il existe une infinit\u00e9 \nd'irrationnels \\(y\\) tels que \\(0\\lt |x-y|\\leq \\frac{1}{10^n}\\). Pour tout entier \\(n\\geq 1\\), il existe une infinit\u00e9 \nd'irrationnels \\(y\\) tels que \\(0\\lt |x-y|\\leq \\frac{1}{10^n}\\). Pour tout entier \\(n\\geq 1\\), il existe une infinit\u00e9 \nd'irrationnels \\(y\\) tels que \\(0\\lt |x-y|\\leq \\frac{1}{10^n}\\). Pour tout entier \\(n\\geq 1\\), il existe une infinit\u00e9 \nd'irrationnels \\(y\\) tels que \\(0\\lt |x-y|\\leq \\frac{1}{10^n}\\). Pour tout entier \\(n\\geq 1\\), il existe une infinit\u00e9 \nd'irrationnels \\(y\\) tels que \\(0\\lt |x-y|\\leq \\frac{1}{10^n}\\). Pour tout entier \\(n\\geq 1\\), il existe une infinit\u00e9 \nd'ir"
    },
    {
        "guid": "6303517c-ecc8-4deb-8785-550de1188bca",
        "model_answer": "To classify traffic signs, which sensor(s) will lead to the best accuracy? (One answer) Lidar Thermal RGB IMU (One answer)\n\n[![enter image description here](https://i.stack.imgur.com/h2Bj.png)](https://i.stack.imgur.com/h2Bj.png)\n\nI'm trying to classify traffic signs based on their color. I'm using the Lidar Thermal RGB IMU, but I'm not sure if it's the best sensor to use.\n\n[![enter image description here](https://i.stack.imgur.com/j2Mf.png)](https://i.stack.imgur.com/j2Mf.png)\n\nI'm trying to classify traffic signs based on their color. I'm using the Lidar Thermal RGB IMU, but I'm not sure if it's the best sensor to use.\n\n[![enter image description here](https://i.stack.imgur.com/hGQh.png)](https://i.stack.imgur.com/hGQh.png)\n\nI'm trying to classify traffic signs based on their color. I'm using the Lidar Thermal RGB IMU, but I'm not sure if it's the best sensor to use.\n\nI'm trying to classify traffic signs based on their color. I'm using the Lidar Thermal RGB IMU, but I'm not sure if it's the best sensor to use.\n"
    }
]