I was a teaching assistant for the AI/ML courses at Berkeley. These are the slides I made for discussion sections.

- Section 1: Search [PDF]
- Section 5: MDPs, RL [PDF]
- Section 6: Random Variables, Conditional Probability, Bayes' Rule [PDF]
- Section 7: Bayes' Nets: Representation, Independence [PDF]
- Section 8: Bayes' Nets: Sampling [PDF]
- Section 9: VPI [PDF]
- Section 10: Markov Models [PDF]
- Section 11: Naive Bayes [PDF]
- Section 12: Perceptrons [PDF]
- Section 13: Feature Maps, K-means [PDF]

- Section 1: Basics and math review [PDF]
- Section 2: Gradient Descent, SVM [PDF]
- Section 3: Decision Theory, Generative Models, Gaussian Classifiers [PDF]
- Section 4: Covariance Matrices [PDF]
- Section 5: Regression [PDF]
- Section 6: Regression, Newton's Method, Risk Functions [PDF]
- Section 7: Bias-variance, Regularization [PDF]
- Section 8: Kernels, Decision Trees [PDF]
- Section 9: Decision Trees, Random Forests [PDF]
- Section 10: Neural Networks [PDF]
- Section 11: Tricks, ConvNets, PCA [PDF]
- Section 12: Unsupervised Learning [PDF]
- Section 13: Recap and advice [PDF]