Stanford AI Course Map 中文 GitHub ↗
← Back to the map

Prerequisites

Prerequisite graph

A coarse prerequisite graph for course ordering, not Stanford's official requirements; check ExploreCourses and the course site.

Core course Related course Arrow: take first → then
Starting point · FoundationsCore MLDirection · AdvancedSystems and applicationsCS 229 · Machine Learning (STATS 229)CS 229Machine Learning (STATS 229)CS 221 · Artificial Intelligence: Principles and TechniquesCS 221Artificial Intelligence: Pr…STATS 202 · Statistical Learning and Data ScienceSTATS 202Statistical Learning and Da…CS 139 · Human-Centered AICS 139Human-Centered AICS 230 · Deep LearningCS 230Deep LearningCS 231N · Deep Learning for Computer VisionCS 231NDeep Learning for Computer …CS 224N · Natural Language Processing with Deep Learning (LINGUIST 284, SYMSYS 195N)CS 224NNatural Language Processing…CS 234 · Reinforcement LearningCS 234Reinforcement LearningCS 228 · Probabilistic Graphical Models: Principles and TechniquesCS 228Probabilistic Graphical Mod…CS 236 · Deep Generative ModelsCS 236Deep Generative ModelsCS 229M · Machine Learning Theory (STATS 214)CS 229MMachine Learning Theory (ST…CS 329Z · Engineering AI AgentsCS 329ZEngineering AI AgentsCS 224W · Machine Learning with GraphsCS 224WMachine Learning with GraphsCS 329H · Machine Learning from Human PreferencesCS 329HMachine Learning from Human…CS 224R · Deep Reinforcement LearningCS 224RDeep Reinforcement LearningCS 336 · Language Modeling from ScratchCS 336Language Modeling from Scra…CS 231A · Computer Vision: From 3D Perception to 3D Reconstruction and BeyondCS 231AComputer Vision: From 3D Pe…CS 279 · Computational Biology: Structure and Organization of Biomolecules and Cells (BIOE 279, BIOPHYS 279, BMDS 245, CME 279)CS 279Computational Biology: Stru…CS 277 · Foundation Models for Healthcare (BMDS 271, RAD 271)CS 277Foundation Models for Healt…CS 329S · Machine Learning Systems DesignCS 329SMachine Learning Systems De…CS 224V · Agentic AICS 224VAgentic AICS 349E · Efficient ML Inference at Scale (EE 339)CS 349EEfficient ML Inference at S…CS 349D · AI Inference InfrastructureCS 349DAI Inference InfrastructureCS 217 · Hardware Accelerators for Machine Learning (EE 244)CS 217Hardware Accelerators for M…MS&E 319 · Efficient Generative ModelsMS&E 319Efficient Generative ModelsEE 292R · AI and Data for Science (CS 292, PSYCH 292R, STATS 282)EE 292RAI and Data for Science (CS…MS&E 203 · Building and Evaluating AI ProductsMS&E 203Building and Evaluating AI …

Core-course prerequisite text

From the course pages
CS 139Human-Centered AI

No strong technical prerequisites; interest in AI products/policy/ethics.

CS 217Hardware Accelerators for Machine Learning (EE 244)

Digital circuits/computer architecture; VLSI or FPGA experience helps.

CS 221Artificial Intelligence: Principles and Techniques

CS 103 (or 103B/X), CS 106B (or 106X), CS 109, and CS 161. The course explicitly says it will not reteach these foundations.

CS 224NNatural Language Processing with Deep Learning (LINGUIST 284, SYMSYS 195N)

Calculus and linear algebra; one of CS 124, CS 221, or CS 229.

CS 224VAgentic AI

One of LINGUIST 180/280, CS 124, CS 224N, CS 224S, or CS 224U.

CS 224WMachine Learning with Graphs

CS 109; one introductory machine learning course.

CS 228Probabilistic Graphical Models: Principles and Techniques

Basic probability; algorithm design and analysis.

CS 229Machine Learning (STATS 229)

Python/NumPy programming (CS 106A/B level); probability (CS 109/MATH 151/STATS 116); multivariable calculus and linear algebra (MATH 51/CS 205).

CS 229MMachine Learning Theory (STATS 214)

MATH 51; STATS 117; CS 229 or STATS 315A.

CS 230Deep Learning

Python programming; linear algebra (matrix/vector operations). CS 229 may be taken concurrently.

CS 231AComputer Vision: From 3D Perception to 3D Reconstruction and Beyond

Linear algebra; basic probability and statistics; programming.

CS 231NDeep Learning for Computer Vision

Fluency in Python/NumPy; calculus and linear algebra (MATH 19/51); basic probability and statistics (CS 109 level).

CS 234Reinforcement Learning

Fluent Python; CS 229 or equivalent ML background; linear algebra and probability.

CS 236Deep Generative Models

At least one of CS 221/228/229/230; probability and calculus; Python programming.

CS 277Foundation Models for Healthcare (BMDS 271, RAD 271)

CS 229/231N/224N-level ML background.

CS 279Computational Biology: Structure and Organization of Biomolecules and Cells (BIOE 279, BIOPHYS 279, BMDS 245, CME 279)

CS 106A; introductory biology/biochemistry.

CS 329HMachine Learning from Human Preferences

Graduate-level ML (CS 229 level); probability and optimization.

CS 329SMachine Learning Systems Design

At least one of CS 229/230/231N/224N; familiarity with one framework (PyTorch/TF/JAX).

CS 329ZEngineering AI Agents

Programming ability; LLM basics (prompting, API use); ML background is a plus.

CS 336Language Modeling from Scratch

Strong programming; deep learning background (CS 224N/CS 231N/CS 230 level); application required, GPU resources recommended.

CS 349DAI Inference Infrastructure

Systems/architecture/ML basics; distributed-systems experience helps.

CS 349EEfficient ML Inference at Scale (EE 339)

Computer architecture, operating systems, ML basics; strong programming.

EE 292RAI and Data for Science (CS 292, PSYCH 292R, STATS 282)

No hard prerequisites; interest in AI + science is enough.

MS&E 203Building and Evaluating AI Products

Upper-level undergraduates/master's students; programming ability; capacity about 48 students (12 teams × 4).

MS&E 319Efficient Generative Models

ML/LLM basics; algorithmic and systems awareness.

STATS 202Statistical Learning and Data Science

Probability/statistics and linear algebra; programming (R/Python).

CS 224RDeep Reinforcement Learning

See the official description (related courses do not have a separate prerequisite write-up).