Syllabus
CSE 473: Introduction to Artificial Intelligence covers principal ideas and developments in artificial intelligence: problem solving and search, game playing, knowledge representation and reasoning, uncertainty, machine learning, and natural language processing.
Table of Contents
About
CSE 473 seeks to introduce foundational concepts in the domain of artificial intelligence across ‘classical’ AI (search, modeling), reinforcement learning, and machine learning (including generative AI).
What this course is:
- A broad introduction to problems and approaches related to machine autonomy and intelligence
- Focused on building students’ theoretical understanding and problem-solving intuition
- A good first ‘AI course’ to take as a CSE student
What this course is not:
- A complete treatment of the fundamentals of machine learning (see CSE 446: Machine Learning)
- ‘How to vibe code’ or about advanced topics in AI
- A course focused (primarily) on the applications and impacts of AI (see CSE 480: Computer Ethics Seminar or CSE 170: Principles, Applications, and Impacts of AI, starting Winter 2027)
Course Components
Lecture
Lectures take place Mondays, Wednesdays, and Fridays 2:30-3:20pm in CSE2 G20. Lectures are recorded and available via Panopto on Canvas.
Practice Problems
Practice problems offer the first opportunity to check your understanding of new material for each lecture. Practice problem worksheets will be provided for each lecture and collected at the end of lecture. Practice problems will be available for review on Gradescope, but must be turned-in at the end of lecture.
Practice problems are graded on completion and can add up to 10% to your final grade (see the section on grading below).
Homework Assignments
Homework assignments are intended to assess your understanding of the key concepts, theories, and approaches introduced in class. The assignments are hosted on Gradescope and include a combination of multiple choice and text and/or math response question types.
Most homework questions can be autograded, but long-form answers will be graded manually by course staff and all homework submissions will be manually checked for grading consistency.
With the exception of Homework 1, homework assignments will be due approximately two weeks after they are released. Each homework assignment will be weighted equally when calculating final grades.
Projects
Projects provide an opportunity to apply your knowledge by implementing algorithms and models discussed in lectures and homework assignments. The projects provide significant scaffolding, command-line tools, programming utilities, and graphical visualizations as you build various AI models.
Most of the projects are autograded, with visibility into the test cases for each question.
For project submissions that encounter issues with the Gradescope autograder, scores will be determined through a manual review of the correctness of your implementation. Each project assignment will be weighted equally when calculating final grades.
Assessments
There will be three assessments for this course. Each assessment will cover the material from the previous third of the class (see the course schedule for more details). Put these dates on your calendar now so that you do not miss them.
The first two assessments will take place during class time on the scheduled day. The third assessment will take place during finals week. In the case that a student must miss an assessment a make-up assessment may be rescheduled. However, make-up assessments may take a different form (oral or computerized) and are at the discretion of the instructor. Contact Megan (mh75@cs.washington.edu) with any concerns.
Grading
Course grades will be determined according to the following weights, with each homework and project assignment weighted equally within its category:
| Course Component | Weight |
|---|---|
| Homework Assignments | ~35% |
| Projects | ~30% |
| Assessments | ~35% |
| Practice | 0-10% |
Your Practice subscore (\(\text{PP}\) is calculated as \(\text{PP} = 10 \cdot \frac{\text{PP_completed}+2}{\text{PP_available}}\). Given your homework, project, and assessment subscores (\(\text{HW}\), \(\text{PROJ}\), and \(\text{ASSESS}\) respectively), your weighted course grade will be computed as follows:
\[\text{weighted_percent} = \frac{0.35 \cdot \text{HW} + 0.3 \cdot \text{PROJ} + 0.35 \cdot \text{ASSESS} + \text{PP}}{100+\text{PP}}\]Late Work
Each homework and project assignment (with the exception of Homework 4) may be submitted up to 2 days after the deadline without penalty. A late penalty of 20 percentage points per day will be applied for each additional day late. For example, a submission made on Monday at 11am for an assignment due the previous Thursday at 11:59pm will earn only 60% of the achieved assignment points after the late penalty is applied.
Homework 4 may be submitted no later than 11:59pm on Wednesday, Dec 16th (the day after the last assessment) to ensure the timely submission of course grades at the end of the quarter.
Requests for deadline extensions will generally be denied, except on a case-by-case basis as required for DRS or religious accommodations. In these cases, extensions must be agreed upon by the student and instructor in advance of the original assignment deadline.
Practice problems may not be submitted late.
Academic Integrity
The goal of this course is to cultivate and assess your ability to understand and apply core concepts in artificial intelligence to a variety of problems—not to showcase the ability of external sources (including AI tools) to approach these problems for you. As such, all submitted work must be your own and reflect your own understanding and effort.
Make sure to familiarize yourself with the course policies on collaboration and AI use below.
All suspected violations of course policies will be reported to the office of Community Standards & Student Conduct (CSSC) for formal investigation. Any student work found by CSSC to be in violation of course policies will receive a score of 0. Repeated violation of course policies across two or more assignments will result a grade of 0 for the course.
Collaboration
While collaboration is encouraged towards understanding course concepts, all course assignments are to be completed individually. In particular, all answers, written work, and code must be your own. Sharing your own assignments solutions (including code) or accessing any solutions (whether from another student, from the internet, or from AI) is prohibited.
AI Use
This course is using the Allen School’s AI as a Reference Tool policy. Roughly this means you may use AI for general course questions and ungraded work, but not for graded assignments, quizzes, exams, or any deliverable that counts toward your grade. The linked full policy contains a lot of helpful information about what this means and how you may responsibly use AI for this course.
Additionally, keep in mind that the use of AI tools is by no means required to succeed on the projects (or anywhere else in the course). In fact, course staff provide the best ‘intelligence’ for any 473-related questions, given we have been fine-tuned on the course material and have been aligned via many quarters of RLHF ;) So consider making Ed or office hours your first stop when you have questions or become stuck.
Resources
CSE 473 offers and uses a variety of resources to help with your learning:
Course Infrastructure
In addition to the course website (which is a great starting point for all things CSE 473), we’ll use the following platforms, which you can access using your UW NetID:
- EdStem serves as the communications hub for the course, including course announcements and asynchronous Q&A.
- Gradescope hosts the course assignments. Practice problem and homework assignment submissions may be made by answering questions directly in Gradescope. Project submissions require uploading the required files (detailed in the project specifications on the course website) to the relevant Gradescope assignment.
- Panopto via Canvas contains the lecture recordings. Lectures can also be viewed live on Panopto.
Textbook
Much of the course aligns with content from Artificial Intelligence: A Modern Approach by Stuart Russell and Peter Norvig (“R&N”). Textbook content can be found online (and linked on EdStem), so you don’t need to buy or rent a physical copy.
Other reading content may be posted on the course website or Ed.
Support
Encountering challenges is a fundamental learning experience, so having questions or getting stuck is entirely expected. Likewise, figuring out how to get your questions answered and get yourself unstuck is part of the learning process. Megan and the course staff are here to support you through that process!
Office hours, the Ed discussion board, are great first stops when you feel stuck or need support. Students are welcome to attend and work at office hours even if they have no direct questions.
Getting Help
At the same time, it’s important to separate the productive challenges that are part of the learning process from unproductive struggle due to factors outside of your control or an unsupportive learning environment. Our ultimate goal as a course staff is to support you with an environment that enables you to be successful, so don’t hesitate to reach out!
If you have any extenuating circumstances (including familial responsibilities, health concerns, etc.), please do not hesitate to contact the course staff (via private Ed message) or Megan (mh75@cs.washington.edu) directly to discuss your situation or concerns.
Likewise, all students are entitled to a respectful and inclusive environment that is conducive to learning. If at any time you are made to feel uncomfortable, disrespected, or excluded (by course staff, other students, or anyone else), please reach out to Megan (mh75@cs.washington.edu) directly. If you prefer not to speak with course staff, you may consider submitting anonymous feedback via the CSE website or contacting the UW Office of the Ombud.
Disability Accommodations
Your experience in this class should not be affected by any disabilities that you may have. The Disability Resources for Students (DRS) office can help you establish accommodations with the course staff.
If you have already established accommodations with DRS, please communicate your approved accommodations to Megan (mh75@cs.washington.edu) at your earliest convenience so we can discuss your needs in this course.
If you have not yet established services through DRS, but have a temporary health condition or permanent disability that requires accommodations (including but not limited to mental health, attention-related, learning, vision, hearing, physical or health impacts), you are welcome to contact DRS. DRS offers resources and coordinates reasonable accommodations for students with disabilities and/or temporary health conditions.
Reasonable accommodations are established through an interactive process between you, your instructor(s) and DRS. It is the policy and practice of the University of Washington to create inclusive and accessible learning environments consistent with federal and state law.
Religious Accommodations
Washington state law requires that UW develop a policy for accommodation of student absences or significant hardship due to reasons of faith or conscience, or for organized religious activities. The UW’s policy, including more information about how to request an accommodation, is available at Religious Accommodations Policy. Accommodations must be requested within the first two weeks of the quarter using the Religious Accommodations Request form.
Acknowledgements
CSE 473 is based on material from CS 188: Artificial Intelligence at UC Berkeley, created by Dan Klein and Pieter Abbeel. The CS 188 Pacman projects were developed by John DeNero and Dan Klein. The lecture illustrations were created by Ketrina Yim.
CSE 473 has been adapted for UW CSE and taught by James Weichert, Jeff Nivala, Taylor Kessler Faulkner, Hanna Hajishirzi, Dan Weld, Luke Zettlemoyer, and Jared Moore. This implementation owes a debt of gratitude to those instructors, and to the course staffs that worked with them.