CS221: Artificial Intelligence: Principles and Techniques

AIWG Statement: This course is participating in the proctoring pilot overseen by the Academic Integrity Working Group (AIWG). The purpose of this pilot is to determine the efficacy of proctoring and develop effective practices for proctoring in-person exams at Stanford. Please review this document as it contains the main questions students might have about the pilot. To find more details on the pilot or the working group, please visit the AIWG's webpage.

Communication: We will use Ed for all communications, which you can access via Canvas. CGOE students: please email stanfordonline-gradprograms@stanford.edu if you need general assistance. Make a public Ed post whenever possible. For extra sensitive matters, you can email cs221-staff-spr2526@cs.stanford.edu, which is visible by only the instructors, head CA, course manager, and student liaison.

Video access disclaimer: Lectures and sections will be recorded and available on Canvas. These recordings might be reused in other Stanford courses, viewed by other Stanford students, faculty, or staff, or used for other education and research purposes. If you have questions or concerns, please contact us.

Academic accommodations: If you need an academic accommodation, contact the Office of Accessible Education (OAE). The OAE will then prepare an OAE letter with the recommended accommodations. Send this letter to cs221-staff-spr2526@cs.stanford.edu by Friday, Apr 18 (Week 3).

General OAE Guidelines:

Contact the OAE to obtain an official accommodation letter if you have a health condition that may impact your coursework.
Only accommodations explicitly stated in your current OAE letter will be accommodated. If you need additional or revised accommodations, you must request an updated letter from the OAE.
The teaching team will not be able to approve any retroactive accommodation requests.
If you have any questions or concerns regarding your accommodations, please contact your disability advisor.
Deadlines and Assignments:
- Students with OAE letters must request a separate extension for each assignment (you cannot auto-apply your OAE extensions to all assignments).
- Students with the standard OAE extension accommodation must request an extension before the original due date, as it says in your OAE letter. Retroactive extension requests will not be approved.
- The teaching team will only approve what is outlined in the OAE letter. If you have any questions or concerns, please reach out to your OAE advisor.

IMPORTANT: If you plan to use your OAE-approved exam accommodations for a specific assessment, students must provide their letter to cs221-staff-spr2526@cs.stanford.edu by:

At least 10 calendar days in advance for accommodations on the midterm exam
May 22, 2026 at 5:00pm for accommodations on the final exam

You need only submit your letter once per quarter. For urgent OAE-related accommodations needs that arise after the deadline, please consult your OAE advisor. If you are not yet registered with OAE, contact the office directly at oae-contactus@stanford.edu.

Collaboration policy and honor code: Please read Stanford's honor code policy. In the context of CS221, you are free to form study groups and discuss homeworks and projects. However, you must write up homeworks and code from scratch independently, and you must acknowledge in your submission all the students you discussed with. The following are considered to be honor code violations:

Looking at the writeup or code of another student.
Showing your writeup or code to another student.
Discussing homework problems in such detail that your solution (writeup or code) is almost identical to another student's solution.
Uploading your writeup or code to a public repository (e.g., GitHub) so that it can be accessed by other students.
Looking at solutions from previous years, either official or written up by another student, or found online.

When debugging code together, you are only allowed to look at the input-output behavior of each other's programs (so you should write good test cases!). We periodically run similarity-detection software over all submitted student programs, including programs from past quarters and any solutions found online on public websites.

Generative AI Policy: Each student is expected to submit their own solutions to the CS221 homeworks. You may use generative AI tools such as Co-Pilot and ChatGPT as you would use a human collaborator. This means that you may not directly ask generative AI tools for answers or copy solutions, and you must acknowledge generative AI tools as collaborators. Additionally, you may not use generative AI tools to "check" your work, even if you wrote it yourself, as this is equivalent to having another student look at your answers. The use of generative AI tools to substantially complete an assignment or exam (e.g. by directly copying) is prohibited and will result in honor code violations. We will be checking students' homework to enforce this policy.

If you use generative AI tools, you must provide a transcript of the interaction (for example, a shared ChatGPT link or screenshots). For example, it is acceptable to use ChatGPT to help with unfamiliar syntax or to debug a specific error, provided that you include the transcript. You may not use generative AI tools that do not support attribution or transcript sharing. For example, using an agentic coding tool such as Codex or Claude Code to build a repository from a project proposal is not allowed. For the final project, we may also review commit history for evidence of overreliance on AI tools.

Honor Code Violations: Anyone violating the honor code policy will be referred to the Office of Community Standards. If you think you violated the policy (it can happen, especially under time pressure!), please reach out to us; the consequences will be much less severe than if we approach you.

Inclusion: The CS221 teaching staff is committed to creating an inclusive and supportive learning environment for all students. Please be respectful to your fellow students, course CAs, and instructors. If you see any problems, please reach out to us early.

Stanford as an institution is committed to the highest quality education, and as your teaching team, our first priority is to uphold your educational experience. To that end we are committed to following the syllabus as written here, including through short- or long-term disruptions, such as public health emergencies, natural disasters, or protests and demonstrations. However, there may be extenuating circumstances that necessitate some changes. Should adjustments be necessary, we will communicate clearly and promptly to ensure you understand the expectations and are positioned for successful learning.

What is this course about? The goal of artificial intelligence (AI) is to tackle complex real-world problems with rigorous mathematical tools. In this course, you will learn the foundational principles and practice implementing various AI systems. Specific topics include machine learning, search, Markov decision processes, game playing, constraint satisfaction, graphical models, and logic.

Prerequisites: This course is fast-paced and covers a lot of ground, so it is important that you have a solid foundation in a number of areas. Here are the basic skills that you need and the classes that teach those skills:

(Required) Programming CS 106A, CS 106B
(Required) Discrete math, mathematical rigor: CS 103
(Required) Probability: CS 109
(Required) Linear algebra: Math 51
(Recommended, but not required) Algorithms: CS 161
(Recommended, but not required) Systems: CS 107

It is less important that you know particular things (e.g., we don't use eigenvectors in this course even though that's a pillar of any linear algebra course), and more important that you've done enough related things that you feel at ease with it. While it is possible to fill in the gaps, this course does move quickly, and ideally you want to be focusing your energy on learning AI rather than catching up on prerequisites. We have made a few prerequisite modules that you can review to refresh your memory, and the first homework (foundations) will allow you to also get some practice on these basics.

Further reading: There are no required textbooks for this class, and you should be able to learn everything from the lecture notes and homeworks. However, if you would like to pursue more advanced topics or get another perspective on the same material, here are some great resources:

Russell and Norvig. Artificial Intelligence: A Modern Approach. A comprehensive reference for all the AI topics that we will cover.
Koller and Friedman. Probabilistic Graphical Models. Covers factor graphs and Bayesian networks (this is the textbook for CS228).
Sutton and Barto. Reinforcement Learning: An Introduction. Covers Markov decision processes and reinforcement learning (free online).
Hastie, Tibshirani, and Friedman. The Elements of Statistical Learning. Covers machine learning from a rigorous statistical perspective (free online).
Tsang. Foundations of Constraint Satisfaction. Covers constraint satisfaction problems (free online).

Note that some of these books use different notation and terminology from this course, so it may may take some effort to make the appropriate connections.

Prerequisites Quiz (0.5%): There is a quiz on the prerequisites that you must take by the due date listed on the Schedule. The quiz is on Gradescope and is open book. You have unlimited attempts and no time limit, and the quiz offers study materials and explanations to help with review.

Homeworks (39.5%): There are weekly homeworks. Each homework is usually centered around an application and has both written and programming parts. Read more about the homework policies here.
1. Foundations [foundations]: page, zip (due Tue Apr 7)
2. Sentiment classification [sentiment]: page, zip (due Tue Apr 14)
3. Route planning [route]: page, zip (due Tue Apr 21)
4. Controlling mountaincar [mountaincar]: (zip) (due Tue Apr 28)
5. Pac-Man [pacman]: (zip) (due Tue May 12)
6. Course scheduling [scheduling]: (zip) (due Tue May 18)
7. Car tracking [car]: (zip) (due Tue May 25)
8. From Language to Logic [logic]: (zip) (due Tue Jun 1)
Homeworks must be typeset and submitted on Gradescope as a PDF. The coding portion will be auto-graded; you get only feedback on a subset of the test cases. Auto-grading is strict, so check your outputs carefully! Read more about the policies around late days (7 total, max 2 per homework), regrades, and submission.
Late day policy (please read): You have 7 total late days across homeworks. You may use a maximum of 2 late days for any single assignment. You are responsible for keeping track of your late days. Please read through the full homework guidelines page for more details.

The point of late days is to give you flexibility to deal with extenuating circumstances (illness, travel, etc). Do not ask for an extension if you have extenuating circumstances; this is what late days are for.

If you join the class late, you will receive a zero on any missed homework assignments.

Exams (60%):
- Exam 1 (30%): Wed May 6th, 6-8 PM on Campus (Location TBD) .
- Exam 2 (30%): Fri Jun 5th, 3:30-5:30 PM on Campus (Location TBD) .
- Both exams will be in-person.
- Exam policy: We will not accommodate Final exam conflicts since the exam is scheduled by the Registrar. All students enrolled in the course must be able to sit for the scheduled exam.
- If you miss an exam, by default you will receive a zero on it.
- If you have an emergency (including illness) that means you have to miss an exam, please contact us via staff mailing list and explain your circumstances. We can't promise to accommodate your emergency, but we will see what we can do. Please keep in mind that if you email us on exam day or the night before, the course staff will be busy with exam logistics and we may take a day or two to get back to you.
- CGOE Students: CGOE students will need to nominate exam monitors for both exams and coordinate the exam process with the CGOE exams team. Please refer to this link for more information on the process. For any additional questions, please reach out to the CGOE exams team.
Extra Credit Options: Students may choose one of the following two extra credit opportunities (not both):
- Project (up to 1.5% extra credit): Use the tools from class to build something interesting of your choice!
  - Projects should be done in groups of 1-4 students.
  - There are 5 milestones for the project throughout the quarter: interest form, proposal, progress report, video, final report.
  - Each project group will be assigned a CA mentor who will give feedback and answer questions.
  - Your project will be graded on the axes described in the project page: task definition, approach, data and experiments, analysis.
  - Your project grade will be scaled to award up to 1.5% extra credit to your final grade: up to +1.5% for an A+ level project, up to +1% for an A/A- level project, up to +0.5% for a B+ level project.
  - For inspiration, check out previous CS221 projects.
  - See the project page for more details.
  - Project Timeline:
    1. Project interest form (due Mon Apr 13)
    2. Project proposal (due Mon Apr 27)
    3. Project progress report (due Thu May 21)
    4. Project final report and video (due Tue Jun 2)
- AI Product Deep Dive (up to 0.75% extra credit): An individual written assignment exploring AI products and their societal implications (approximately half the time commitment of the project).
  - Must be completed individually.
  - Due Tue Jun 2 (same as the project final report).
  - More details on this assignment will be released soon.

Ed (up to 1% extra credit): Please help answer your classmates's questions on Ed! You will be awarded extra credit depending on how substantial and helpful you were on Ed.

See also course calendar for office hours and other events.

Pre-requisite review materials: see Canvas for pre-recorded videos from previous iterations.

	Monday	Tuesday	Wednesday	Thursday	Friday	Saturday	Sunday
Week 1	Mar 30	Mar 31	Apr 1	Apr 2	Apr 3	Apr 4	Apr 5
Modules Week 1 HW1 Released [Foundations]	Lecture 1: Overview 10:30am - 12:20pm		Lecture 2: Learning I 10:30am - 12:20pm		Problem Session 1 10:30am - 11:20am
Week 2	Apr 6	Apr 7	Apr 8	Apr 9	Apr 10	Apr 11	Apr 12
Modules Week 2 HW2 Released [Sentiment]	Lecture 3: Learning II 10:30am - 12:20pm	HW1 due 11:59pm Prerequisites quiz due 11:59pm	Lecture 4: Learning III 10:30am - 12:20pm		Problem Session 2 10:30am - 11:20am
Week 3	Apr 13	Apr 14	Apr 15	Apr 16	Apr 17	Apr 18	Apr 19
Modules Week 3 HW3 Released [Route]	Lecture 5: Search I 10:30am - 12:20pm Project interest form due 11:59pm	HW2 due 11:59pm	Lecture 6: Search II 10:30am - 12:20pm		Problem Session 3 10:30am - 11:20am
Week 4	Apr 20	Apr 21	Apr 22	Apr 23	Apr 24	Apr 25	Apr 26
Modules Week 4 HW4 Released [MountainCar]	Lecture 7: MDPs I 10:30am - 12:20pm	HW3 due 11:59pm	Lecture 8: MDPs II 10:30am - 12:20pm		Problem Session 4 10:30am - 11:20am
Week 5	Apr 27	Apr 28	Apr 29	Apr 30	May 1	May 2	May 3
Modules Week 5 HW5 Released [Pacman]	Lecture 9: Games I 10:30am - 12:20pm Project proposal due 11:59pm	HW4 due 11:59pm	Lecture 10: Games II 10:30am - 12:20pm		Problem Session 5 10:30am - 11:20am
Week 6	May 4	May 5	May 6	May 7	May 8	May 9	May 10
Modules Week 6	Lecture 11: Factor Graphs 10:30am - 12:20pm		Lecture 12: Beam Search 10:30am - 12:20pm Exam 1 6-8pm		Problem Session 6 10:30am - 11:20am
Week 7	May 11	May 12	May 13	May 14	May 15	May 16	May 17
Modules Week 7 HW6 Released [Scheduling]	Lecture 13: Bayesian Networks I 10:30am - 12:20pm	HW5 due 11:59pm	Lecture 14: Bayesian Networks II 10:30am - 12:20pm		Problem Session 7 10:30am - 11:20am
Week 8	May 18	May 19	May 20	May 21	May 22	May 23	May 24
Modules Week 8 HW7 Released [Car]	Lecture 15: Bayesian Networks III 10:30am - 12:20pm	HW6 due 11:59pm	Lecture 16: Logic I 10:30am - 12:20pm	Project progress report due 11:59pm	Problem Session 8 10:30am - 11:20am
Week 9	May 25	May 26	May 27	May 28	May 29	May 30	May 31
Modules Week 9 HW8 Released [Logic]	Memorial Day No lecture	HW7 due 11:59pm	Lecture 17: Logic II 10:30am - 12:20pm		Problem Session 9 10:30am - 11:20am
Week 10	Jun 1	Jun 2	Jun 3	Jun 4	Jun 5	Jun 6	Jun 7
Modules Week 10	Lecture 18: Conclusion/Summary/Future of AI 10:30am - 12:20pm	HW8 due 11:59pm Project final report and video due 11:59pm AI Product Deep Dive due 11:59pm (Please note: only ONE of Project and AI Product Deep Dive are due — NOT both.) Final Exam Review Skilling Auditorium 3:00 - 4:20pm			Exam 2 3:30-5:30pm