CS 189/289A: Intro to Machine Learning

UC Berkeley, Fall 2025

Ed Gradescope Lectures Playlist Additional Accommodations Office Hours Queue Content Repository Class Drive

Welcome to Week 4 of CS 189/289A!

Lectures will be broadcast at this link.

Please note that the size of this course is not expanding, and we cannot predict whether you will get off the waitlist.

Schedule

Week 1

Wed Aug 27
First Day of Classes
Thu Aug 28
Lecture 1 Introduction + ML Problem Framing
Lecture Participation 1 Slido
Fri Aug 29

Week 2

Mon Sep 1
Tue Sep 2
Lecture 2 Data Tools
Lecture Participation 2 Slido
Wed Sep 3
Discussion 1 Introduction to ML
Thu Sep 4
Lecture 3 ML Mechanics, Terminology, and Techniques
Lecture Participation 3 Slido
Fri Sep 5
Homework 1 Intro to ML (notebook, materials)
Homework 1 Written Math Refresher

Week 3

Mon Sep 8
Tue Sep 9
Lecture 4 K-Means and Probability
Lecture Participation 4 Slido
Wed Sep 10
Discussion 2 Working with Data & ML Techniques
Thu Sep 11
Lecture 5 Density Estimation and Gaussian Mixture Models
Lecture Participation 5 Slido

Week 4 (Current Week)

Mon Sep 15
Tue Sep 16
Lecture 6 GMM Recap and Linear Regression (1)
Lecture Participation 6 Slido
Wed Sep 17
Discussion 3 Probability & KMeans & Linear Regression
Thu Sep 18
Lecture 7 Linear Regression (2)
Fri Sep 19
Homework 1 - Part 1 and Homework 1 Written Due

Week 5

Mon Sep 22
Tue Sep 23
Lecture 8 Linear Regression (3)
Wed Sep 24
Discussion 4 Linear Regression & MLE
Thu Sep 25
Lecture 9 Logistic Regression (1)
Fri Sep 26
Homework 2 Chatbot Arena
Homework 1 - Part 2 due

Week 6

Mon Sep 29
Tue Sep 30
Lecture 10 Logistic Regression (1)
Wed Oct 1
Discussion 5 Logistic Regression & MLE
Thu Oct 2
Lecture 11 Gradient Descent (1)
Fri Oct 3
Homework 2 Part 1 due

Week 7

Mon Oct 6
Tue Oct 7
Lecture 12 Gradient Descent (2)
Wed Oct 8
Discussion 6 Gradient Descent
Thu Oct 9
Lecture 13 Neural Networks (1): Build Non-linearity, Architecture, Activation Functions
Fri Oct 10

Week 8

Mon Oct 13
Tue Oct 14
Lecture 14 Neural Networks (2): PyTorch NN and Backpropagation
Wed Oct 15
Discussion 7 Neural Networks Basics
Thu Oct 16
Lecture 15 Neural Networks (3): Batch Normalization, Initialization, and Regularization
Fri Oct 17
Homework 3 Backprop and Neural Nets
Homework 2 Part 2 due

Week 9

Mon Oct 20
Tue Oct 21
Midterm Exam Midterm (7:00 - 9:00pm)
Wed Oct 22
Discussion 8 Neural Networks & Backpropagation
Thu Oct 23
Lecture 16 Architectures: CNN
Fri Oct 24
Homework 3 - Part 1 due

Week 10

Mon Oct 27
Tue Oct 28
Lecture 17 Architectures: RNN
Wed Oct 29
Discussion 9 CNN
Thu Oct 30
Lecture 18 Transformers
Fri Oct 31
Halloween

Week 11

Mon Nov 3
Tue Nov 4
Lecture 19 Generative models - NLP (LLM)-1
Wed Nov 5
Discussion 10 RNN Architecture and Transformer
Thu Nov 6
Lecture 20 Generative models - NLP (LLM)-2
Fri Nov 7
Homework 4 CNNs and Transformers
Homework 3 Part 2 due

Week 12

Mon Nov 10
Tue Nov 11
Veterans Day No Lecture
Wed Nov 12
Discussion 11 Transformers & LLMs
Thu Nov 13
Lecture 21 Guest Lecture - Prof. Efros
Fri Nov 14
Homework 4 - Part 1

Week 13

Mon Nov 17
Tue Nov 18
Lecture 22 Dimensionality Reduction (PCA)
Wed Nov 19
Discussion 12 Generative Models & NLP
Thu Nov 20
Lecture 23 Auto-encoder + GAN basic (1)
Fri Nov 21

Week 14

Mon Nov 24
Tue Nov 25
Lecture 24 Auto-encoder + GAN basic (2)
Wed Nov 26
Discussion 13 PCA & Auto-encoders
Thu Nov 27
Thanksgiving No Lecture
Fri Nov 28
Homework 5 Pre-training + instruction-tuning
Homework 4 - Part 2 due

Week 15

Mon Dec 1
Tue Dec 2
Lecture 25 Guest Lecture
Wed Dec 3
Discussion 14 GANs & Course Review
Thu Dec 4
Lecture 26 Closing
Fri Dec 5

Week 16 - RRR Week

Mon Dec 8
Finals Week
Tue Dec 9
Study Day
Wed Dec 10
Study Day
Thu Dec 11
Study Day
Fri Dec 12
Homework 5 DUE

Week 17 - Finals Week

Tue Dec 16
Final Exam Final (8:00-11:00 AM)