CS 189/289A at UC Berkeley
Introduction to Machine Learning
Lectures: Tues & Thurs 2-3:30 pm online (Berkeley Academic Guide page)
Week 1 Overview
Maximum Likelihood and Multivariate Gaussians
- Discussion 0 (solution)
- Homework 0
- Lecture 8/31 (slides) (video)
- Lecture 9/2 (slides) (video)
Week 2 Overview
Linear Regression and Classification
- Discussion 1 (solution)
- Homework 1 (zip)
- Lecture 9/7 (slides) (video)
- Lecture 9/9 (slides) (slides) (video)
Week 3 Overview
Logistic Regression, Neural Networks, Backpropagation, and SGD
- Discussion 2 (solution)
- Homework 1 (zip)
- Lecture 9/14 (slides) (slides) (video)
- Lecture 9/16 (slides) (video)
Week 4 Overview
Multiway Classification, Decision Theory, Bias-Variance, Over- and Under-Fitting
- Discussion 3 (solution)
- Homework 2 (zip)
- Lecture 9/21 (slides) (slides) (video)
- Lecture 9/23 (slides) (video)
Week 5 Overview
ROC Curves, Precision/Recall, Dimensionality Reduction, and PCA
- Discussion 4 (solution)
- Homework 2 (zip)
- Lecture 9/28 (slides) (video)
- Lecture 9/30 (slides) (video)
Week 6 Overview
t-SNE and Clustering
- Discussion 5 (solution)
- Homework 3
- Lecture 10/5 (slides) (video)
- Lecture 10/7 (slides) (video)
Week 8 Overview
Support Vector Machines and Convolutional Neural Networks
Week 9 Overview
Applications in Vision and Nearest Neighbor
Week 10 Overview
Metric Learning and Transformers
Week 11 Overview
Language Models
Week 12 Overview
Applications in Computational Biology and Graphical Models
Week 13 Overview
Graphical Models
Week 14 Overview
Causality
Discussions
- Discussion 0: Math review and self-assessment (solution)
- Discussion 1: MLE, linear regression, and MAP (solution)
- Discussion 2: MAP and regularized regression (solution)
- Discussion 3: Logistic regression and backpropagation (solution)
- Discussion 4: Decision theory and bias/variance (solution)
- Discussion 5: Principal components analysis (solution)
- Discussion 6: Midterm review (solution)
Expand
Lecture Slides and Videos
- 8/26: Welcome and Introduction
(slides) (slides) (video) - 8/31: Maximum Likelihood Estimation
(slides) (video) - 9/2: Multivariate Gaussians
(slides) (video) - 9/7: Linear Regression
(slides) (video) - 9/9: Linear Regression continued, Classification
(slides) (slides) (video) - 9/14: Logistic Regression, Neural Networks
(slides) (slides) (video) - 9/16: Neural Networks, Backpropagation and SGD
(slides) (video) - 9/21: Multiway Classification, Decision Theory
(slides) (slides) (video) - 9/23: Bias-variance, Over- and under-fitting
(slides) (video) - 9/28: ROC Curves, Precision/Recall
(slides) (video) - 9/30: Dimensionality Reduction, PCA
(slides) (video) - 10/5: t-SNE
(slides) (video) - 10/7: Clustering
(slides) (video) - 10/12: Kernel Methods
(slides) (video) - 10/14: SVMs part 1
(slides) (video)
Expand