COS 324 - Introduction to Machine Learning

Princeton University, Fall 2022

About

This website contains the course notes for COS 324 - Introduction to Machine Learning at Princeton University. The notes were prepared by professors Sanjeev Arora, Danqi Chen and undergraduates Simon Park, and Dennis Jacob.

If you find any typos or mistakes, or have any comments or feedback, please submit them here. It will be helpful if you specify the version of the notes. The last modified date can be found on the copyright page.

Last Updated: September 07, 2024

Errata

The currently maintained version of the errata can be found here.

Full Version

Introduction to Machine Learning

Individual Chapters

1. Supervised Learning

Ch 1: Linear Regression: An Introduction
Ch 2: Statistical Learning: What It Means to Learn
Ch 3: Optimization via Gradient Descent
Ch 4: Linear Classification
Ch 5: Exploring “Data Science” via Linear Regression

2. Unsupervised Learning

Ch 6: Clustering
Ch 7: Low-Dimensional Representation
Ch 8: n-Gram Language Models
Ch 9: Matrix Factorization and Recommender Systems

3. Deep Learning

Ch 10: Introduction to Deep Learning
Ch 11: Feedforward Neural Network and Backpropagation
Ch 12: Convolutional Neural Network

4. Reinforcement Learning

Ch 13: Introduction to Reinforcement Learning
Ch 14: Markov Decision Process
Ch 15: Reinforcement Learning in Unknown Environment

5. Advanced Topics

Ch 16: Machine Learning and Ethics
Ch 17: Deep Learning for Natural Language Processing

6. Mathematics for Machine Learning

Ch 18: Probability and Statistics
Ch 19: Calculus
Ch 20: Linear Algebra

This work is licensed under a Creative Commons Attribution-NonCommercial-NoDerivs 2.0 Generic License