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.
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):
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:
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.
- Homeworks (60%):
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:
- Exam (20%): The exam is a three-hour written exam that will
test your knowledge and problem-solving skills on all preceding lectures and homeworks.
You cannot use any external aids
except one double-sided page of notes.
If you have a major conflict (e.g., an academic conference),
submit a request to take it at another (earlier) time.
Your request must be submitted by Wed Oct 31.
Date: Tue Nov 27 from 6pm to 9pm
Location: Memorial Auditorium
For SCPD students, your exams will be distributed through the SCPD office once you have set up an exam monitor.
- Project (20%): 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 up to three.
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:
See the project page for more details.
Regardless of the group size, all groups must submit the same basic amount of work as detailed in each milestone.
Of course, the experiments may not always be successful,
so we will cut the smaller groups more slack,
while larger groups are expected to be more thorough in their experiments.
For inspiration, we have made
previous CS221 projects available for viewing.
You will be awarded with up to 2% extra credit
if you answer other students' questions in a substantial and helpful way.
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.
You are encouraged to use LaTeX to writeup your homeworks
(here's a template
), but this is not a requirement. You will receive
one (1) bonus point
for submitting a typed written assignment (e.g. LaTeX, Microsoft Word).
We will accept scanned handwritten assignments but they will not receive the bonus point.
The grader runs on Python 2.7, which is not guaranteed to work with newer versions (Python 3) or older versions (below 2.7).
Please use Python 2.7
to develop your code.
The programming assignments are designed to be run
in GNU/Linux environments, such
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 original
operating on the student's
cardinal.stanford.edu, and must submit their
cardinal.stanford.edu as well. The
final grading will be run on GNU/Linux servers.
The submitted code will not be graded if it has one of the following issues:
- The original
grader.py script (operating on the
submission.py) does not exit normally
cardinal.stanford.edu. Note that calls such as
os._exit() may cause the program to exit abnormally, as may excessive resource usage.
Also note that Python packages outside the standard library are not guaranteed to work.
- 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
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 Percy or the head CA;
the consequences will be much less severe than if we approach you.
All assignments (homework problems and project milestones) must be submitted using the submit script by
11pm (23:00, not 23:59)
Please note that the submission script only works on cardinal
Copy your submission files
<assignment ID>.pdf and
cardinal.stanford.edu. You can use a graphical interface
Fugu) or the following command:
scp <your submission file(s)> <your SUNetID>@cardinal.stanford.edu:
ssh <your SUNetID>@cardinal.stanford.edu
For Windows, you can use
Make sure you use the binary transfer mode, as the ASCII transfer mode will silently damage PDF files!
Make sure the original
grader.py script (operating on your
submission.py) runs correctly on cardinal. (Otherwise, the code will not be graded.)
/usr/bin/python /usr/class/cs221/WWW/submit.py <assignment ID> <directory with your submission files>
For example, if the assignment ID is
and you are in the same directory as your submission files, type:
/usr/bin/python /usr/class/cs221/WWW/submit.py foundations ./
You are allowed to submit an assignment a maximum of ten (10) times.
Each submission will replace the previous.
Since we do not accept the assignments from other submission methods (e.g., email),
please make sure you can use the submit script. Do not wait until the deadline.
If anything goes wrong, please ask a question on Piazza or contact a course assistant.
Do not email us your submission.
Partial work is better than not submitting any work.
You can check here for confirmation of your submission.
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 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
For the project milestones, make sure the same one member of your
group submits on behalf of the entire group. The submission should include a
group.txt file which should contain the SUNetIDs of the entire
group, one per line. Do not include your names!
An assignment is $\lceil d \rceil$ days late if it is turned in $d$ fractional days late
(note that this means if you are $1$ second late, $d = 1/(24 \times 60 \times 60)$ and it is 1 day late).
You have eight (8) late days
in total that can be distributed among the assignments (except for p-poster, p-peer, and p-final)
There is a maximum of two (2) late days that can be used per assignment.
If you exceed this limit by $k$ hours,
then you will incur a multiplicative penalty factor of $\max(1 - k/5, 0)$.
For example, if you get $40$ points and turn in your homework 2 days + 1.5 hours after the deadline,
then your effective score is $40(1 - 1.5/5) = 28$.
If you exceed $5$ hours, you will receive $0$ points.
You get a zero after all your late days run out, but we reserve the right to give partial credit in extenuating circumstances.
If you believe that the course staff made an objective error in grading,
then you may submit a regrade request. To do this, you must come in person
to the owner CA in charge of the given homework or exam problem. If you cannot come
to the office hours of the owner CA, you can come to the office hours of a CA who was
a grader for the homework or exam. If you cannot come to the office hours of any
grader CA, you may ask any CA for a regrade at office hours. SCPD students may ask
for regrades at any online office hours.
Any requests submitted over email or on Piazza will be ignored.
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. If the regrade request is valid, the CA will add your request
to the list, which will get processed.