Introduction to Machine Learning

University of California, Berkeley, Fall 2023

Welcome to CS 189/289A! This class covers theoretical foundations, algorithms, methodologies, and applications for machine learning. Topics may include supervised methods for regression and classication (linear models, trees, neural networks, ensemble methods, instance-based methods); generative and discriminative probabilistic models; deep learning models including CNNs, Transformers, graph neural networks for vision and language tasks; and Markovian models for reinforcement learning and robotics.

Here are the Gradescope/Ed codes (you should self-enroll in these). We won’t post any materials on bCourses.

Also, the Professors will post slides prior to lecture at this Google Drive folder (for faster access). The material here is redundant with the website, but it may take up to a day or two for the website to get updated with the slides after lecture. The “Post-Lecture” subfolder contains updates to slides that the Professors may make right after lecture.

Note: The topics for future lectures, discussions, and HWs are tentative and may be moved around, changed, or removed.

Overview

Week 1

8/24 Lecture 1: Introduction and Logistics Slides

Week 2

8/28 Homework 1: Math Review (Due 9/8 11:59pm) PDF
8/29 Lecture 2: Maximum Likelihood Estimation Slides
8/30 Discussion 0: Math Pre-Requisites Review PDF, Solutions
8/31 Lecture 3: Multivariate Gaussians Slides

Week 3

9/5 Lecture 4: Linear Regression 1 Slides
9/6 Discussion 1: MLE & Gaussians PDF, Solutions
9/7 Lecture 5: Linear Regression 2 Slides
9/9 Homework 2: Linear/Logistic Regression & Classification (Due 9/22 11:59pm) PDF

Week 4

9/12 Lecture 6: Classification - Generative & Discriminative Slides
9/13 Discussion 2: Linear Regression PDF, Solutions
9/14 Lecture 7: Logistic Regression & Neural Networks Slides

Week 5

9/19 Lecture 8: Backpropagation and Gradient Descent 1 Slides
9/20 Discussion 3: Classification & Logistic Regression PDF, Solution, Walkthrough
9/21 Lecture 9: Backpropagation and Gradient Descent 2 Handout
9/23 Homework 3: Neural Networks (Due 10/6 11:59pm) PDF, Files

Week 6

9/26 Lecture 10: Neural Networks - CNNs, Batch Norm, & ResNets Slides
9/27 Discussion 4: Neural Networks and Training PDF
9/28 Lecture 11: Neural Netowkrs - Attention & Transformers  

Week 7

10/3 Lecture 12: Dimensionality Reduction & PCA  
10/4 Discussion 5: Convolution and Attention  
10/5 Lecture 13: t-SNE  
10/7 Homework 4: Dimensionality Reduction & Decision Theory (Due 10/20 11:59pm)  

Week 8

10/10 Lecture 14: Clustering  
10/11 Discussion 6: Dimensionality Reduction Techniques  
10/12 Lecture 15: Multiway Classification, Decision Theory, & Model Evaluation  
10/13 Midterm (7-9pm, Pimentel 1)  

Week 9

10/17 Lecture 16: Bias-Variance Tradeoff & Over/Under-Fitting  
10/18 Discussion 7: Clustering and Decision Theory  
10/19 Lecture 17: Nearest Neighbors & Metric Learning  
10/21 Homework 5: Bias/Variance, Nearest Neighbors, Decision Trees (Due 11/3 11:59pm)  

Week 10

10/24 Lecture 18: Decision Trees & Ensembling  
10/25 Discussion 8: Bias/Variance and Nearest Neighbors  
10/26 Lecture 19: Hidden Markov Models & Graphical Models 1  

Week 11

10/31 Lecture 20: Hidden Markov Models & Graphical Models 2  
11/1 Discussion 9: Decision Trees and HMMs Intro  
11/2 Lecture 21: Markov Decision Processes  
11/4 Homework 6: Markovian Models & Reinforcement Learning (Due 11/17 11:59pm)  

Week 12

11/7 Lecture 22: Reinforcement Learning  
11/8 Discussion 10: HMMs Advanced and MDPs  
11/9 Lecture 23: Robotics and Machine Learning  

Week 13

11/14 Lecture 24: Language and Vision Applications  
11/15 Discussion 11: Robotics, Language, & Vision  
11/16 Lecture 25: Graph Neural Networks & Rotational Equivariance 1  
11/18 Homework 7: Graph Neural Networks & Applications of Deep Learning (Due 12/1 11:59pm)  

Week 14

11/21 Lecture 26: Graph Neural Networks & Rotational Equivariance 2  
11/22 Discussion 12: Graph Neural Networks  
11/23 No Lecture (Thanksgiving)  

Week 15

11/28 Lecture 27: Special Topics - Computational Biology  
11/30 Lecture 28: Special Topics - Causality  

Week 16 (RRR Week)

No lectures or discussions this week

Week 17 (Finals Week)

12/12 Final Exam (8-11am, Location TBD)