Cheatsheet for the ETH Zurich Reliable and Interpretable Artificial Intelligence class autumn 2018. This cheatsheet was created by me based on the lecture material and is not an offical document of the class.
The following topics are included:
- Fast Gradient Sign Method (FGSM)
- Projected Gradient Descent (PGD)
- Training Neural Networks with Logic
- Certify AI with Abstract Domains
- Visualization of NN
- Probabilistic Programming
Feel free to report mistakes or fork the repo to update the cheat sheet.
Download the latest pdf version here