Course Description This course provides a broad introduction to machine learning and statistical pattern recognition. Topics include: supervised learning (generative/discriminative learning, parametric/non-parametric learning, neural networks, support vector machines); unsupervised learning (clustering, dimensionality reduction, kernel methods); learning theory (bias/variance tradeoffs, practical advice); reinforcement learning and adaptive control. The course will also discuss recent applications of machine learning, such as to robotic control, data mining, autonomous navigation, bioinformatics, speech recognition, and text and web data processing.
Note: This schedule is tentative and subject to change.
| Date | Session | Topic | Details |
|---|---|---|---|
| September 22, 2025 | Lecture 1 | Introduction | Problem Set 0 Released |
| September 24, 2025 | Lecture 2 | Supervised learning setup. LMS. | Problem Set 1 Released |
| September 26, 2025 | TA Lecture 1 | Linear Algebra Review | |
| September 29, 2025 | Lecture 3 | Weighted Least Squares. Logistic regression. Newton's Method | |
| October 1, 2025 | Lecture 4 | Dataset split; Exponential family. Generalized Linear Models. | Problem Set 0 (Due at 11:59 pm PT - Ungraded) |
| October 2, 2025 | Discussion 1 | TBD | |
| October 3, 2025 | TA Lecture 2 | Probability Review | |
| October 6, 2025 | Lecture 5 | Bias-variance tradeoff, regularization | Final Project Proposal (Due at 11:59 pm PT) |
| October 8, 2025 | Lecture 6 | Gaussian discriminant analysis. Naive Bayes, Laplace Smoothing. | Problem Set 2 Released Problem Set 1 (Due at 11:59 pm PT) |
| October 9, 2025 | Discussion 2 | TBD | |
| October 10, 2025 | TA Lecture 3 | Python/Numpy | |
| October 13, 2025 | Lecture 7 | Kernels. SVM. | |
| October 15, 2025 | Lecture 8 | K-Means. GMM. Expectation Maximization | |
| October 16, 2025 | Discussion 3 | TBD | |
| October 17, 2025 | TA Lecture 4 | Evaluation Metrics | |
| October 20, 2025 | Lecture 9 | Decision trees | |
| October 22, 2025 | Lecture 10 | Boosting | Problem Set 3 Released Problem Set 2 (Due at 11:59 pm PT) |
| October 23, 2025 | Discussion 4 | Practice Midterm Question Walk-through | |
| October 24, 2025 | TA Lecture 5 | Midterm Review | |
| October 27, 2025 | Lecture 11 | Neural Networks 1 | |
| October 29, 2025 | Lecture 12 | Neural Networks 2 (backprop) | |
| October 30, 2025 | MIDTERM | MIDTERM EXAM | Location TBD (6-9 pm PT) No TA Lecture (Midterm Week) |
| November 3, 2025 | Lecture 13 | ML Advice | |
| November 5, 2025 | Lecture 14 | Basic concepts in RL, value iteration, policy iteration | Problem Set 4 Released Problem Set 3 (Due at 11:59 pm PT) |
| November 6, 2025 | Discussion 5 | TBD | |
| November 7, 2025 | TA Lecture 6 | Deep Learning (Convnets) | |
| November 10, 2025 | Lecture 15 | Model-based RL, value function approximator | |
| November 12, 2025 | Lecture 16 | PCA | Final Project Milestone (Due at 11:59 pm PT) |
| November 14, 2025 | TA Lecture 7 | Transformers | |
| November 17, 2025 | Lecture 17 | Large language models — learning tasks, language modeling, embeddings, transformers | |
| November 19, 2025 | Lecture 18 | Large language models — RAG, fine-tuning, prompt optimization, safety | Problem Set 4 (Due at 11:59 pm PT) |
| December 1, 2025 | Lecture 19 | Fairness, algorithmic bias, explainability, privacy | |
| December 3, 2025 | Lecture 20 | Fairness, algorithmic bias, explainability, privacy | |
| December 5, 2025 | Final Project Report | Final Project Report (Due at 11:59 pm PT) | |
| December 10, 2025 | Final Project Poster Session | Final Project Poster Session (3:30 pm - 6:30 pm PT) |