XCS221 Executable Lectures

This repository contains all the executable lectures, made using edtrace.

No local setup required! Use the links below to access the compiled, production-ready lecture notes directly in your browser.

If you notice any problems or have any questions, please file a GitHub issue or submit a pull request.

---

Module 1: Introduction

Foundations

• welcome
• history

Module 2: Machine Learning

Tensors and Einops

• tensors

Foundational ML

• backpropagation
• linear_regression

Classification

• linear_classification

Language Models

• language_models

Deep Learning

• deep_learning

Module 3: Search

Foundational Search

• foundational_search

Heuristic Search

• heuristic_search

Module 4: Reinforcement Learning

Markov Decision Processes (MDPs)

• mdp

Foundational RL

• foundational_rl

Policy Gradients

• policy_gradients

Module 5: Games

Game Trees & Adversarial Search

• games

Temporal Difference (TD) Learning

• td_learning

Game Theory

• game_theory

Module 6: Bayesian Networks & Probabilistic Inference

Bayesian Networks

• bayesian_networks

Probabilistic Inference

• probabilistic_inference

Parameter Learning

• parameter_learning

Module 7: Logic

Propositional Logic

• propositional_logic

First-order Logic

• first_order_logic

Module 8: Language Models

Introduction to Language Models

• language_models

Module 9: AI, Ethics, and Society

Ethics

• ethics

Economics of AI

• economics

---

For Course Developers Only

⚠️ The instructions below are intended for the course development team and are not needed by students or contributors. They are used to update the GitHub-hosted lecture URLs.

Prerequisites

macOS:

brew install graphviz
uv sync

Linux:

sudo apt-get install graphviz
uv sync

Running an Executable Lecture

python -m edtrace.execute -m welcome

This will generate a .json file that wires into the static frontend and is served via GitHub Pages.