|
|
CS 229 |
|
Syllabus |
- Introduction (1 class) Basic concepts.
- Supervised learning. (7 classes) Supervised learning setup. LMS.
- Learning theory. (3 classes) Bias/variance tradeoff. Union and Chernoff/Hoeffding bounds.
- Unsupervised learning. (5 classes) Clustering. K-means.
- Reinforcement learning and control. (4 classes) MDPs. Bellman equations.
Logistic regression. Perceptron. Exponential family.
Generative learning algorithms. Gaussian discriminant analysis. Naive Bayes.
Support vector machines.
Model selection and feature selection.
Ensemble methods: Bagging, boosting.
Evaluating and debugging learning algorithms.
VC dimension. Worst case (online) learning.
Practical advice on how to use learning algorithms.
EM. Mixture of Gaussians.
Factor analysis.
PCA (Principal components analysis).
ICA (Independent components analysis).
Value iteration and policy iteration.
Linear quadratic regulation (LQR). LQG.
Q-learning. Value function approximation.
Policy search. Reinforce. POMDPs.
|
Dates for assignments |
- Assignment 1: Out 10/05. Due 10/19.
- Assignment 2: Out 10/19. Due 11/02.
- Assignment 3: Out 11/02. Due 11/16.
- Assignment 4: Out 11/16. Due 12/07.
- Midterm: 11/09, 6-9pm. Location: 320-105 and Cemex Auditorium
- Term project: Proposals due 10/21 (5pm). Milestone due 11/18 (5pm). Poster presentations on 12/14 (8.30am-11.30am); final writeup due on 12/16 (11:59pm, no late days).
|
Comments to cs229-qa@cs.stanford.edu. |