CS221: Artificial Intelligence: Principles and Techniques

Communication: We will use Ed for all communications, and will send out an access link through Canvas. We encourage all students to use Ed, either through public or private posts. However, if you have an issue that you would like to discuss privately, you can also email us at cs221-spr2021-staff@lists.stanford.edu, which is read by only the faculty, course coordinator, head CA, and student liaison.

Academic accommodations: If you need an academic accommodation, you should initiate the request with the Office of Accessible Education (OAE). The OAE will evaluate the request, recommend accommodations, and prepare a letter for faculty. Students should contact the OAE as soon as possible and at any rate in advance of assignment deadlines, since timely notice is needed to coordinate accommodations. It is the student's responsibility to reach out to the teaching staff regarding the OAE letter. Please send your letters to cs221-spr2021-staff@lists.stanford.edu by Friday, April 16 (week 3).

COVID-19 update: CS221 will be offered online Spring 2021. This quarter will be difficult, with remote learning, the COVID-19 pandemic, and other events in the US and around the globe. We expect and understand that students will face challenges beyond what a normal in-person quarter would entail. To better support students, we are adapting the course format and introducing several new class activities this year. These are experimental, so please let us know if you have any feedback or suggestions on how we can better support you and make the best out of the quarter.

Modules (videos and slides): We will have an intro lecture to the week's material on Monday during class time. The rest of the week's material will be delivered through modules, pre-recorded course videos that students can watch at their own time. Each week's modules are listed in the schedule and can be accessed here.
Live lectures: During our class time each Monday, we will have a live lecture with faculty, which consists of an introduction to the week's module as well as a Q&A.
Problem sessions: During our class time each Wednesday, we will hold a problem session where a CA will guide students to work together through practice problems.
Office hours with faculty and CAs: Our CAs will hold office hours in both open and 1:1 settings. Our faculy will hold 1:1 OHs in the weeks that they are teaching the lecture.
- Open OH: These are open to all students and require no appointment.
- 1:1 OH: These will be appointment-based so that students need not wait in the queue. See our calendar for times and sign up links. Please contact us through Ed if you want to schedule one but cannot find an available slot.
We will have two different types of office hours with the CAs:
- Homework OH: Office hours designated specifically for questions about the homework.
- General OH: Office hours where the CAs answer all non-homework questions, including those about modules, exams, and projects.

We are also making three changes to the course structure:

Shorter Exams: To lower the stress of having a single high-stakes assessment, we will have a shorter midterm instead of a 3-hour one.
Alternative Non-Project Grading Scheme: The course project is not required this quarter. We have two different grading schemea, one for the students who would like to pursue the project and one for those who don't. The grade breakdowns is explained further in the coursework section.

Platforms: Besides Ed, we will use a combination of Zoom and Nooks to hold class activities. All exam, homework, and project submissions will be handled through Gradescope, where you will also find your grades. The links and access codes can be accessed through Canvas.

Time/Location: All class activities and office hours are in our class calendar. All following times are in Pacific Time (PT):

Modules: Each week's modules will be posted in our schedule at the start of the week.
Live Lectures (Zoom): Mondays 1:00-2:20pm (class time).
Problem Sessions (Nooks): Wednesdays 1:00-2:20pm (class time).
Office Hours (Nooks): Throughout the week; sign up links are on our class calendar.

Instructors:

Chelsea Finn
(Office Hours)
In Weeks 1-2 and 4-6

Nima Anari
(Office Hours)
In Weeks 3 and 7-10

Course Assistants:

Amelie Byun
Course Coordinator

Dilara Soylu
(General OH)
Head CA

Kris Kaya
(General OH)
Student Liaison

Kevin Chen
(Homework OH)

Fenglu Hong
(Homework OH)

Mike Wu
(General OH)

Moo Jin Kim
(Homework OH)

Vincent Li
(Homework OH)

Sam Lowe
(General OH)

Zhengping Zhou
(General OH)

Edward Xu
(Homework OH)

Ho Kyung Sung
(Homework OH)

What is this course about? What do web search, speech recognition, face recognition, machine translation, autonomous driving, and automatic scheduling have in common? These are all complex real-world problems, and the goal of artificial intelligence (AI) is to tackle these with rigorous mathematical tools. In this course, you will learn the foundational principles that drive these applications and practice implementing some of these systems. Specific topics include machine learning, search, game playing, Markov decision processes, constraint satisfaction, graphical models, and logic. The main goal of the course is to equip you with the tools to tackle new AI problems you might encounter in life.

Prerequisites: This course is fast-paced and covers a lot of ground, so it is important that you have a solid foundation on both the theoretical and empirical fronts. You should have taken the following classes (or their equivalents):

Programming (CS 106A, CS 106B, CS 107)
Discrete math (CS 103)
Probability (CS 109)
Linear algebra (Math 51)

Reading: There is no required textbook 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 books:

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. Available free online.
Hastie, Tibshirani, and Friedman. The elements of statistical learning. Covers machine learning. Available free online.
Tsang. Foundations of constraint satisfaction. Covers constraint satisfaction problems. Available free online.

Bear in mind that some of these books can be quite dense and use different notation terminology, so it might take some effort to connect up with the material from class.

Video access disclaimer: A portion of class activities will be given and recorded in Zoom. For your convenience, you can access these recordings by logging into the course Canvas site. 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, please contact a member of the teaching team.

Grading There are three types of main coursework in the class: homeworks, exams and the final project. We have two different grading schemes: with and without the final project. If you decide to do the final project, we will calculate your grade under both of the grading schemes, and pick the best. The extra credit opportunites we have are the same for both of these grading schemes. We also have some extra credit opportunities available in a few homeworks.

With Project

Homeworks: 50%.

Exams: 30%.

Project: 20%.

Without Project

Homeworks: 60%.

Exams: 40%.

Homeworks: There will be weekly homeworks with both written and programming parts. Each homework is centered around an application and will also deepen your understanding of the theoretical concepts. Some homeworks will have a competition component; winners will receive extra credit. Here are all the homework deadlines:
Exams: There will be two exams that will test your knowledge and problem-solving skills on preceding lectures and homeworks.
Exam 1
- Date: released at 2:30PT on Wednesday, May 5; due at 2:30PT on Thursday, May 6.
- Length: 100 minutes. Designed to be completed within 80 minutes, with an additional 20-minute leeway for scanning and/or uploading.
- Format: The exam will be open book and distributed and administered through Gradescope and will be available for 24 hours. Students can choose any block of time within the designated window above to take the exam.
Exam 2
- Date: released at 2:30PT on Wednesday, June 2; due at 2:30PT on Thursday, June 3.
- Length: 120 minutes. Designed to be completed within 80 minutes, with an additional 40-minute leeway for scanning and/or uploading.
- Format: Same as Exam 1.
Conflict: If you have a major time conflict for either exam (e.g., an academic conference), you should let us know privately via email by Friday, January 29 (week 3).

Project: The final project provides an opportunity for you to use the tools from class to build something interesting of your choice. Projects should be done in groups of one to four students. Each project group will be assigned a CA mentor who will give feedback and answer questions, and thus the project will also be an opportunity for mentorship. See the project page for more details. For inspiration, we have also made some previous CS221 projects available for viewing.
The project will be something that you work on throughout the course and we have set up some milestones to help you along the way:
- Project interest form [p-interest] (due Fri April 16)
- Project proposal [p-proposal] (due Fri April 30)
- Project progress report [p-progress] (due Fri May 21)
- Project final report and video [p-final] (due Fri June 4)
Regardless of the group size, all groups must submit the work detailed in each milestone and will be graded on the same criteria. Although we allow 1-2 person project groups, we encourage groups of 3-4 members. We encourage teams of 3-4 students because this size typically best fits the expectations for CS 221 projects. We expect each team to submit a completed project (even for team of 1 or 2). All projects require that students spend time gathering data, and setting up the infrastructure to reach an end result. A 3 or 4 person team can share these tasks much better, allowing the team to focus more on the interesting results and discussion in the project. Each member of the team should contribute in both technical and non-technical components of the project. We will provide resources on Ed and the project page that can help you find group members.
Extra Credit: You will be awarded with up to 3% extra credit based on your contributions to the class on Ed.

Homeworks

Written assignments: Homeworks should be written up clearly and succinctly; you may lose points if your answers are unclear or unnecessarily complicated. Here is an example of what we are looking for. Written homework must be typeset using LaTeX, Microsoft Word, Pages for Mac, or an equivalent program, and submitted as a PDF. We strongly encourage you to use LaTeX: there are user-friendly web interfaces like Overleaf. See this getting started guide. Figures may be hand-drawn, so long as they are included in a typeset PDF. If you're not sure where to start with formatting your written solutions, we recommend using this template as a starting point. You can copy and paste its contents into an Overleaf project or upload it directly.

Programming assignments: The grader runs on Python 3.7, which is not guaranteed to work with older versions (e.g., Python 2.7). Please use Python 3.7 to develop your code.

The programming assignments are designed to be run in GNU/Linux environments. Most or all of the grading code may incidentally work on other systems such as MacOS or Windows, and students may optionally choose to do most of their development in one of these alternative environments. However, no technical support will be provided for issues that only arise on an alternative environment. Moreover, no matter what environment is used during development, students must confirm that their code (specifically, the student's submission.py) runs on Gradescope.

The submitted code will not be graded if it has one of the following issues:

The original grader.py script (operating on the submitted submission.py) may not exit normally if you use calls such as quit(), exit(), sys.exit(), and os._exit(). Also note that Python packages outside the standard library are not guaranteed to work. Therefore, do not use packages like numpy, scikit-learn, and pandas.
The code reads external resources other than the files given in the assignment.
The code is malicious. This is considered a violation of the honor code. The score of the assignment will be zero (0) and the incident will be reported to the Office of Judicial Affairs.

Collaboration policy and honor code: 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 answer.
Uploading your writeup or code to a public repository (e.g. github, bitbucket, pastebin) so that it can be accessed by other students.
Looking at solutions from previous years' homeworks - either official or written up by another student.

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!). It is important to remember that even if you didn't copy but just gave another student your solution, you are still violating the honor code, so please be careful. We periodically run similarity-detection software over all submitted student programs, including programs from past quarters and any solutions found online on public websites. Anyone violating the honor code will be referred to the Office of Judicial Affairs. If you feel like you made a mistake (it can happen, especially under time pressure!), please reach out to the instructor or the head CA; the consequences will be much less severe than if we approach you.

Office hours debugging policy: Only for the first four assignments (i.e., up to and including Blackjack), the homework CAs can look at your code and provide debugging support if you have been stuck on a problem in the programming portion for a long time. If you need debugging help, please carefully read the Ed post titled "Debugging Template and FAQs" before asking for support.

Submission

Electronic Submission: All assignments are due at 11pm (23:00, not 23:59) Pacific time on the due date.
Assignments are submitted through ">Gradescope. Do not submit your assignment via email. If anything goes wrong, please ask a question on Ed or contact a course assistant. If you need to sign up for a Gradescope account, please use your @stanford.edu email address. You can submit as many times as you'd like until the deadline: we will only grade the last submission. Submit early to make sure your submission runs properly on the Gradescope servers. Gradescope will run grader.py on the programming questions and give you feedback on non-hidden test cases. You are responsible for checking that your program runs properly on these cases. You will not get credit otherwise. If anything goes wrong, please ask a question on Ed or contact a course assistant. Do not email us your submission. Partial work is better than not submitting any work.

For assignments with a programming component, we will automatically sanity check your code in some basic test cases, but we will grade your code on additional test cases. Important: just because you pass the basic test cases, you are by no means guaranteed to get full credit on the other, hidden test cases, so you should test the program more thoroughly yourself!

Unless the assignment instructs otherwise, all of your code modifications should be in submission.py and all of your written answers in <assignment ID>.pdf. Upload the former to Gradescope under the "Programming" section, and the latter under the "Written" section.

For the project milestones, make sure that all members of your group submit. The submission should include a group.txt file which should contain the SUNetIDs of the entire group, one per line.

Late days: A homework is $\lceil d \rceil$ days late if it is turned in $d$ days past the due date (note that this means if you are $1$ second late, $\lceil d \rceil = 1$ and it is 1 day late). You have seven (7) late days in total that can be distributed among the homeworks without penalty. After that, the maximum possible grade is decreased by 25% each day (so the best you can do with $d = 1$ is 75%). As an example, if you are out of late days and submit one day late, a 90 will be capped at a 75, but a 72 will not be changed. Note that we will only allow a max of $d = 2$ late days per homework, though, so if $d > 2$ then we will not accept your submission. Gradescope is set up to accept written and programming submissions separately. Late days are calculated per-assignment, with the number of late days used depending on the later submission. So, if the programming part is $1$ day late and the written part is $2$ days late, then that will count as using $2$ late days.

No late days can be taken for exams; you can start the timed exams any time during the one-dat window.

Regrades: If you believe that the course staff made an objective error in grading, then you may submit a regrade request for the written part of your homework or quiz. Remember that even if the grading seems harsh to you, the same rubric was used for everyone for fairness, so this is not sufficient justification for a regrade. It is also helpful to cross-check your answer against the released solutions. If you still choose to submit a regrade request, click the corresponding question on Gradescope, then click the "Request Regrade" button at the bottom. Any requests submitted over email or in person will be ignored. Regrade requests for a particular assignment are due by Monday 4pm, one week after the grades are returned. Note that we may regrade your entire submission, so that depending on your submission you may actually lose more points than you gain.

Nooks links included in the schedule below assume you have already signed into our Nooks space following our class specific link shared on Canvas and Ed.

	Monday	Tuesday	Wednesday	Thursday	Friday	Saturday	Sunday
Week 1	Mar 29	Mar 30	Mar 31	Apr 1	Apr 2	Apr 3	Apr 4
Modules Introduction Prerequisites Machine Learning I Homework [Foundations]	Live Lecture: Introduction (Chelsea) 1:00-2:20pm		Problem Session 1 1:00-2:20pm [Problems] [Video] [Solutions]	Python Tutorial & Homework Introduction 10:30am-11:50am [Colab Link] [Recording]
Week 2	Apr 5	Apr 6	Apr 7	Apr 8	Apr 9	Apr 10	Apr 11
Modules Machine Learning II Homework [Sentiment]	Live Lecture: Machine Learning II (Chelsea) 1:00-2:20pm Foundations HW due		Problem Session 2 1:00-2:20pm [Problems] [Video] [Solutions]			Homework Party 10:00am-12:00pm Project Mixer 6:00-8:00pm	Homework Party 1:00-3:00pm
Week 3	Apr 12	Apr 13	Apr 14	Apr 15	Apr 16	Apr 17	Apr 18
Modules Search Homework [Reconstruct]	Live Lecture: Search (Nima) 1:00-2:20pm Sentiment HW due		Problem Session 3 1:00-2:20pm [Problems] [Slides] [Video] [Solutions]		Project Interest Form Due Final Study List Deadline	Homework Party 6:00-8:00pm	Homework Party 6:00-8:00pm
Week 4	Apr 19	Apr 20	Apr 21	Apr 22	Apr 23	Apr 24	Apr 25
Modules MDPs Homework [Blackjack]	Live Lecture: MDPs (Chelsea) 1:00-2:20pm Reconstruct HW due		Problem Session 4 1:00-2:20pm [Problems] [Slides] [Video] [Solutions]			Homework Party 10:00am-12:00pm	Homework Party 1:00-3:00pm
Week 5	Apr 26	Apr 27	Apr 28	Apr 29	Apr 30	May 1	May 2
Modules Games Homework [Pacman]	Live Lecture: Games (Chelsea) 1:00-2:20pm Blackjack HW due		Problem Session 5 1:00-2:20pm [Problems] [Slides] [Video] [Solutions]		Project Proposal due	Homework Party 10:00am-12:00pm	Homework Party 1:00-3:00pm
Week 6	May 3	May 4	May 5	May 6	May 7	May 8	May 9
Modules N/A	No lecture Pacman HW due		No problem session Exam 1 released at 2:30PT	Exam 1 Due at 2:30PT		Project Party 10:00-11:00am
Week 7	May 10	May 11	May 12	May 13	May 14	May 15	May 16
Modules Factor Graphs Homework [Scheduling]	Live Lecture: Factor Graphs (Nima) 1:00-2:20pm		Problem Session 6 1:00-2:20pm [Problems] [Slides] [Video] [Solutions]			Homework Party 10:00am-12:00pm	Homework Party 1:00-3:00pm
Week 8	May 17	May 18	May 19	May 20	May 21	May 22	May 23
Modules Bayesian Networks Homework [Car]	Live Lecture: Bayesian Networks (Nima) 1:00-2:20pm Scheduling HW due		Problem Session 7 1:00-2:20pm [Problems] [Slides] [Video] [Solutions]		Project Progress Report due	Homework Party 10:00am-12:00pm	Homework Party 1:00-3:00pm
Week 9	May 24	May 25	May 26	May 27	May 28	May 29	May 30
Modules Logic Conclusion Homework [Logic]	Live Lecture: Logic (Nima) 1:00-2:20pm Car HW due		Problem Session 8 1:00-2:20pm [Problems] [Slides] [Video] [Solutions]			Homework Party 6:00-8:00pm	Homework Party 6:00-8:00pm
Week 10	May 31	Jun 1	Jun 2	Jun 3	Jun 4	Jun 5	Jun 6
Modules N/A	No lecture Logic HW due		No problem session Exam 2 released at 2:30PT	Exam 2 due at 2:30PT	Project Final Report due