ovgu_deeplearning

Git repo for Weekly Programming Tasks of Deep Learning OVGU class 2020 Summer semester

Class website - https://ovgu-ailab.github.io/idl2020s/

Assignment Team:

1. Sanjeeth Busnur
2. Aditya Dey
3. Suraj Shashidhar

Colab Notebooks Link - https://drive.google.com/drive/folders/14uh0RF-oWJP0cMcuLQ-FKvuFOMGJ9UCB?usp=sharing

Main References for individual assignments

Task 1 - MLP:

Display multiple images in a loop: https://stackoverflow.com/questions/41210823/using-plt-imshow-to-display-multiple-images

Setting the hidden layers hyper parameter: https://stats.stackexchange.com/questions/181/how-to-choose-the-number-of-hidden-layers-and-nodes-in-a-feedforward-neural-netw

Matmul error: https://stackoverflow.com/questions/54255431/invalidargumenterror-cannot-compute-matmul-as-input-0zero-based-was-expected

Task 2 - Tensorboard:

View gradients in Tensorboard: https://stackoverflow.com/questions/50033312/how-to-monitor-gradient-vanish-and-explosion-in-keras-with-tensorboard

Task 3 - CNN:

Displaying Feature maps: https://github.com/gabrielpierobon/cnnshapes/blob/master/README.md

Task 4 - Densenets:

Densenets: https://github.com/liuzhuang13/DenseNet

Task 5 - RNN:

Basic RNN: https://www.tensorflow.org/guide/keras/rnn

Text Generation with RNN: https://www.tensorflow.org/tutorials/text/text_generation

Task 6 - Realistic RNN with loss masking:

Generating mask: https://www.tensorflow.org/api_docs/python/tf/sequence_mask

Task 8 - Autoencoders:

Adding gaussian noise - https://stackoverflow.com/questions/43382045/keras-realtime-augmentation-adding-noise-and-contrast

Image augemntation library: https://github.com/aleju/imgaug/tree/master/imgaug Logistic regression using Keras - https://medium.com/hackernoon/logistic-regression-with-tensorflow-and-keras-83d2487aed89

Task 10 - Adverserial Attacks and Training:

Overview blog 1: https://medium.com/@ml.at.berkeley/tricking-neural-networks-create-your-own-adversarial-examples-a61eb7620fd8 | https://blog.ycombinator.com/how-adversarial-attacks-work/

Overview Blog 2: https://openai.com/blog/adversarial-example-research/#:~:text=Machine%20Learning-,with%20Adversarial,like%20optical%20illusions%20for%20machines. | https://distill.pub/2018/building-blocks/