CS 189/289A: Intro to Machine Learning
UC Berkeley, Spring 2026
Wheeler 150, Tuesdays and Thursdays 2pm-3:30pm
Course staff email: cs189-instructors@berkeley.edu. This email is monitored by the instructors, the head TAs, and a few lead TAs.
Welcome to Week 8 of CS 189/289A!
Schedule
| Wk. | Date | Lecture | Recommended Reading | Sections | HW |
|---|---|---|---|---|---|
| 1 |
Tue Jan 20 | 1. Introduction + ML problem framing |
1.1 (The Impact of Deep Learning), 1.2 (A Tutorial Example), 1.3 (A Brief History of Machine Learning) | No Section | |
|
Thu Jan 22 | 2. Data Tools PDF / Video |
||||
| 2 |
Tue Jan 27 | 3. Machine Learning Mechanics - Terminology and Techniques PDF / Video |
1.1 (The Impact of Deep Learning), 1.2 (A Tutorial Example), 1.2.1 (Synthetic data), 1.2.2 (Linear models), 1.2.3 (Error function), 1.2.4 (Model complexity), 1.2.5 (Regularization), 1.2.6 (Model selection), 3.5.3 (Nearest-neighbours), 4.1 (Linear Regression), 4.1.1 (Basis functions), 5.4.3 (Logistic regression), 9.1 (Inductive Bias), 9.1.2 (No free lunch theorem) | 1. Discussion |
Homework 1
(due Fri Feb 20) Part 1: Written / Part 1: Coding / Part 2: Coding |
|
Thu Jan 29 | 4. Clustering, Probability Review PDF / Video |
2.1 (The Rules of Probability), 2.1.2 (The sum and product rules), 2.1.3 (Bayes' theorem), 2.1.6 (Independent variables), 2.2 (Probability Densities), 15.1 (K-means Clustering) | |||
| 3 |
Tue Feb 03 | 5. Intro to Maximum Likelihood Estimation, Multivariate Gaussians, Mixture of Gaussians PDF / Video |
2.3.2 (Likelihood function), 3.1.3 (Multinomial distribution), 3.2 (Multivariate Gaussian), 3.2.1 (Geometry of Gaussian), 3.2.7 (Maximum likelihood), Appendix C (Lagrange multipliers), Optional: 2.2.2 (Expectations and covariances), 3.2.9 (Mixtures of Gaussians) | 2. Discussion |
|
|
Thu Feb 05 | 6. Multivariate Gaussians & Mixture of Gaussians PDF / Video |
2.2.2 (Expectations and covariances), 3.1.3 (Multinomial distribution), 3.2 (Multivariate Gaussian), 3.2.1 (Geometry of Gaussian), 3.2.9 (Mixtures of Gaussians), 15.2 (Mixtures of Gaussians), 15.3 (Mixture model log-likelihood), Appendix C (Lagrange multipliers) | |||
| 4 |
Tue Feb 10 | 7. Mixture of Gaussians & Linear Regression PDF / Video |
1.2 (A Tutorial Example), 2.3.4 (Linear regression), 3.2.9 (Mixtures of Gaussians), 4.1.1 (Basis functions), 4.1.2 (Likelihood function), 4.1.3 (Maximum likelihood), 4.1.4 (Geometry of least squares), 15.2 (Mixtures of Gaussians), 15.2.1 (Likelihood function), Appendix A.3 (Matrix Derivatives) | 3. Discussion |
|
|
Thu Feb 12 | 8. Linear Regression PDF / Video |
1.2.2 (Linear models), 1.2.3 (Error function), 1.2.5 (Regularization), 1.2.6 (Model selection), 2.1.3 (Bayes' theorem), 2.3.4 (Linear regression), 2.6.2 (Regularization), 4.1.1 (Basis functions), 4.1.2 (Likelihood function), 4.1.3 (Maximum likelihood), 4.1.4 (Geometry of least squares), 4.1.6 (Regularized least squares), 9.2 (Weight Decay), 9.2.2 (Generalized weight decay), Appendix A.3 (Matrix Derivatives) | |||
| 5 |
Tue Feb 17 | 9. Linear Regression & Regularization PDF / Video |
4. Discussion |
||
|
Thu Feb 19 | 10. Finish Linear Regression & Regularization PDF / Video |
1.2.6 (Model selection), 4.1.2 (Likelihood function), 4.1.6 (Regularized least squares), 5.3 (Generative Classifiers), 5.3.1 (Continuous inputs), 5.3.2 (Maximum likelihood solution), 5.3.3 (Discrete features), 9.2 (Weight Decay), 9.2.2 (Generalized weight decay) | |||
| 6 |
Tue Feb 24 | 11. Classification PDF / Video |
5.0 (Introduction), 5.1 (Discriminant Functions), 5.1.1 (Two classes), 5.1.2 (Multiple classes), 5.1.3 (1-of-K coding), 5.1.4 (Least squares for classification), 5.3 (Generative Classifiers), 5.3.1 (Continuous inputs), 5.3.2 (Maximum likelihood solution), 5.3.3 (Discrete features) | 5. Discussion |
Homework 2
(due Fri Mar 13, 11:59 PM PT) Assignment |
|
Thu Feb 26 | 12. Logistic Regression, Classifier Accuracy PDF / Video |
5.2.2 (Expected loss), 5.2.5 (Classifier accuracy), 5.2.6 (ROC curve), 5.4 (Discriminative Classifiers), 5.4.1 (Activation functions), 5.4.2 (Fixed basis functions), 5.4.3 (Logistic regression), 5.4.4 (Multi-class logistic regression) | |||
| 7 |
Tue Mar 03 | 13. Conv. + Momentum + Adam + Stochastic Gradient Descent Notes / Video |
7.1 (Error Surfaces), 7.1.1 (Local quadratic approximation), 7.2 (Gradient Descent Optimization), 7.2.2 (Batch gradient descent), 7.2.3 (Stochastic gradient descent), 7.2.4 (Mini-batches), 7.3 (Convergence), 7.3.1 (Momentum), 7.3.2 (Learning rate schedule), 7.3.3 (RMSProp and Adam), Appendix A.4 (Eigenvectors) | 6. Discussion |
|
|
Thu Mar 05 | 14. MLE, MAP and Bias-Variance Trade-off Notes / Video |
2.6.1 (Model parameters), 2.6.2 (Regularization), 3.1.1 (Bernoulli distribution), 4.1.2 (Likelihood function), 4.1.6 (Regularized least squares), 4.3 (The Bias-Variance Trade-off), 5.4.3 (Logistic regression) | |||
| 8 |
Tue Mar 10 | 15. Learning with Gradient Descent Notes / Video |
7.1 (Error Surfaces), 7.1.1 (Local quadratic approximation), 7.2.2 (Batch gradient descent), 7.2.3 (Stochastic gradient descent), 7.2.4 (Mini-batches), 7.3 (Convergence), 7.3.1 (Momentum), 7.3.2 (Learning rate schedule), 7.3.3 (RMSProp and Adam), Appendix A.4 (Eigenvectors) | 7. Discussion |
|
|
Thu Mar 12 | 16. Entropy, Information and Logistic Regression Notes / Video |
2.5.1 (Entropy), 2.5.5 (Kullback-Leibler divergence), 5.3.1 (Continuous inputs), 5.4.3 (Logistic regression), 5.4.4 (Multi-class logistic regression) | |||
| 9 |
Tue Mar 17 | 17. Midterm (7pm-9pm) |