Artificial Intelligence Graduate Program Course Planning

Earning the certificate: To complete the Artificial Intelligence Graduate Program, you must complete one required course and
three elective courses. You must receive a B (3.0) or better in each course in order to continue taking courses via the Non-Degree
Option Program.

General Prerequisites: Before beginning, you should have strong backgrounds in programming (C/C++, python), linear algebra,
calculus, as well as statistics and probability. Each course may have individual prerequisites. You can find more detailed
information about each course via the course webpage on Stanford Online.

Required Courses (Complete at least 1) Schedule is subject to change

COURSE NAME & NUMBER PREREQS UNITS AUTUMN WINTER SPRING SUMMER

Artificial Intelligence: Principles and Techniques

3-4 Online Online Online
CS221

Machine Learning
4 Online Online Online
CS229

Elective Courses (Complete at most 3) Schedule is subject to change

COURSE NAME & NUMBER PREREQS UNITS AUTUMN WINTER SPRING SUMMER

Decision Making Under Uncertainty

3-4 Online
AA228
Principles of Robot Autonomy
3-4 Online
AA274A
Computational Logic
3 Online
CS157
Introduction to Robotics
3 Online
CS223A
Natural Language Processing w/ Deep Learning
CS221 4 Online
CS224N
Natural Language Understanding CS221 or
4 Online
CS224U CS224N
Machine Learning with Graphs
3-4 Online
CS224W
Probabilistic Graphical Models: Principles and Techniques
4 Online
CS228
CS229
Deep Learning
may take 4 Online Online Online
CS230
concurrently
COURSE NAME & NUMBER PREREQS UNITS AUTUMN WINTER SPRING SUMMER

Computer Vision: From 3D Reconstruction to Recognition

4 Online
CS231A

Convolutional Neural Networks for Visual Recognition

CS229 4 Online
CS231N
Reinforcement Learning CS229 or
3 Online
CS234 equivalent

CS228,
Deep Generative Models CS221,
3 Online
CS236 CS229 or
CS230
Principles of Robot Autonomy II
AA274A 4 Online
CS237B
Deep Multi-task and Meta Learning CS229 or
3 Online
CS330 equivalent
Machine Learning Theory
CS229 3-4 Online
STATS214
 Your Program Road Map
You have up to three academic years to complete the program. You should expect to spend a minimum 15-20
hours per week on course work.

There are many pathways through the Artificial Intelligence Graduate program. Your path will depend in part on
what you’re interested in studying. We recommend starting with CS221 because it is a prerequisite for many of
the elective courses. Due to its difficulty, we do not advise taking CS229 unless you have taken other courses via
the Non-Degree Option Program.

Below are sample schedules, depending on which quarter you choose to begin. These schedules may not all be
possible every year as class offerings vary:

Autumn Winter Spring Summer Autumn Winter Spring

Autumn
Start CS221 CS224N CS224U CS229
(NLP)
CS221 CS221
Winter
CS228 or or CS236
Start
CS229 CS229
CS221 CS221
Spring
or or CS330 CS234
Start
CS229 CS229
Summer CS221 CS221
Start or AA274A CS237B or
(Robotics) CS229 CS229
Summer CS221 CS221
Start or or CS231A CS231N
(Vision) CS229 CS229
 Preparing for the Program
If you have little programming experience, you should consider Stanford’s Foundations in Computer Science
Graduate Program or the Introductory Programming Graduate Program. Completing the program will satisfy the
programming prerequisites for CS221: Artificial Intelligence: Principles and Techniques. If you have no prior
programming experience you will need to begin with CS106A and CS106B.

If you don’t have the required mathematics, you should consider these Stanford courses: for probability and
statistics, CS109 or STATS116; for Linear Algebra, ENGR108. Not all the mathematics prerequisites can be met
through Stanford courses. We recommend exploring options at your local community college.

If you need a refresher to prepare, you should consider the following self-study resources. This list includes
resources that other learners have found useful. Their inclusion does not imply any specific endorsement by
SCPD.

Mathematics
● Mathematics for Machine Learning series from Imperial College London
● Stanford CS229 Linear Algebra Review and Reference
● MIT Single Variable Calculus
● MIT Multivariable Calculus
● MIT Linear Algebra course
● MIT Mathematics for Machine Learning
● The Matrix calculus for Deep Learning

Statistics and Probability

● Stanford CS229 Review of Probability Theory
● Stanford CS229 Statistics and Probability Refresher

Python
● Introduction to Computer Science and Programming Using Python
● Applied Data Science with Python
● Stanford CS231n Python/Numpy Tutorial

If you are interested in self-study, you can browse our free recordings of Stanford AI courses.