Acknowledgement: This repository is largely adopted from maxim5/cs229-2018-autumn, we thank the author sincerely for organizing the lecture notes and problem sets!
- Course website and syllabus
- Autumn 2018 (available for watching at youtube, bilibili)
- Lecture 2: Linear regression and gradient descent
- Lecture 3: Locally weighted logistic regression
- Lecture 4: Perceptron, Generalized linear models (softmax regression)
- Lecture 5: Generative Learning Algorithm (GDA, Naive Bayes)
- Lecture 6: Support Vector Machine
- Lecture 7: Kernel Methods
- Lecture 8: Cross Validation, Bayesian Statistics
- Lecture 9: Bias-Variance Analysis
- Lecture 10: Decision Trees
- Lecture 11: Introduction to Neural Networks
- Lecture 12: Back-propagation
- Lecture 13: Advice for debugging learning algorithms
- Lecture 14: Introduction to unsupervised-learning (K-means, Mixture of Gaussians)
- Lecture 15: Expectation-Maximization Algorithm (Factor Analysis)
- Lecture 16: Principal Component Analysis & Independent Component Analysis
- Lecture 17: Markov Decision Process, Tabular Reinforcement Learning
- Lecture 18: Continuous State MDPs, Fitted Value Iteration
- Lecture 19: Linear Dynamical System
- Lecture 20: RL Debugging and Diagnostics
├─Notes
│ ├─Lecture_Notes
│ └─Written_Notes
├─ProblemSet
│ ├─PS0
│ ├─PS1
│ ├─PS2
│ ├─PS3
│ └─PS4
└─ProblemSet_Solutions
├─PS0
├─PS1
├─PS2
├─PS3
└─PS4
- Lecture Notes are the notes provided by course staff, file is named after its specific content for convenient look-up.
- Written Notes are the hand-written notes I took while listening to the lectures, include core derivations that are omitted during class time.
For basic introduction to matrix theory (namely, how to differentiate a matrix function w.r.t. a matrix), read these two supplement materials, they are more detailed than some textbooks and theses: