CS 189/289A at UC Berkeley

# Introduction to Machine Learning

Lectures: Tuesday, Thursday 2-3:30 pm in Li Ka Shing 245 *(Berkeley Academic Guide page)*

### Week 2 Overview

## Maximum Likelihood Estimation

- Discussion 0 (solution)
- Homework 0 (zip)
- Lecture 8/30 (slides)
- Lecture 9/1 (slides)

### Week 3 Overview

## Linear Regression

- Discussion 1 (solution)
- Homework 0 (zip)
- Homework 1 (zip)
- Lecture 9/6 (slides)
- Lecture 9/8 (slides)

### Week 4 Overview

## Classification

- Discussion 2 (solution)
- Homework 1 (zip)
- Lecture 9/13 (slides)
- Lecture 9/15 (slides)
- Lecture 9/15 (slides)

### Week 5 Overview

## Gradient Descent and Backpropagation

- Discussion 3 (solution)
- Homework 1 (zip)
- Homework 2 (zip)
- Lecture 9/22 (slides)

### Week 6 Overview

## Evaluating Models

- Discussion 4 (solution)
- Homework 2 (zip)
- Lecture 9/27 (slides)
- Lecture 9/29 (slides)

### Week 7 Overview

## Dimensionality Reduction

- Discussion 5 (solution)
- Homework 2 (zip)
- Homework 3
- Lecture 10/4 (slides)
- Lecture 10/6 (slides)

### Week 8 Overview

## Clustering

- Discussion 6 (solution)
- Homework 3
- Lecture 10/11 (slides)
- Lecture 10/13 (slides)

### Week 9 Overview

## Decision Trees

- Discussion 7 (solution)
- Homework 4
- Lecture 10/18 (slides)
- Lecture 10/20 (slides)

### Week 10 Overview

## Convolutional Neural Networks and Vision

- Discussion 8 (solution)
- Homework 4
- Lecture 10/25 (slides)

### Week 11 Overview

## Transformers and Natural Language Processing

### Week 12 Overview

## Graph Neural Networks and Computational Biology

### Week 14 Overview

## Reinforcement Learning

### Week 15 Overview

## Robotics and Causality

## Discussions

- Discussion 0: Math review and self-assessment (solution)
- Discussion 1: Maximum Likelihood Estimation, Regularization, LASSO (solution)
- Discussion 2: MLE vs. MAP, Regularization (solution)
- Discussion 3: Gradient Descent, Neural Networks (solution)
- Discussion 4: Backpropagation (solution)
- Discussion 5: Risk Minimization, Bias-Variance Tradeoff (solution)
- Discussion 6: PCA (solution)
- Discussion 7: MLE/MAP Review (solution)
- Discussion 8: Decision Trees (solution)
- Discussion 9: Convolution, Transformers (solution)
- Discussion 10: PGM, MDP (solution)

Expand

## Homeworks

- Homework 0: Math review and self-assessment (zip)
- Homework 1: Gaussians, MLEs, Linear Regression (zip)
- Homework 2: Implementing a neural network in NumPy (zip)
- Homework 3: Decision theory, Bias-variance tradeoff
- Homework 4: Dimensionality reduction, K-nn, Trees
- Homework 5: MLPs, CNNs and Transformer on MNIST

Expand

## Lecture Slides and Videos

- 8/25: Welcome and Introduction

(slides) (slides) - 8/30: Maximum Likelihood Estimation

(slides) - 9/1: Multivariate Gaussians

(slides) - 9/6: Linear Regression I

(slides) - 9/8: Linear Regression II

(slides) - 9/13: Logistic Regression I

(slides) - 9/15: Neural Networks

(slides) - 9/15: Neural Networks I

(slides) - 9/22: Neural Networks II

(slides) - 9/27: Decision Theory

(slides) - 9/29: Bias/Variance, Overfit

(slides) - 10/4: Dimensionality Reduction, PCA

(slides) - 10/6: PCA, tSNE

(slides) - 10/11: Clustering

(slides) - 10/13: Nearest Neighbors

(slides) - 10/18: Decision Trees, Ensembles

(slides) - 10/20: CNN, ResNet

(slides) - 10/25: Attention, Transformers

(slides)

Expand