CS 486/686: Introduction to Artificial Intelligence (Spring 25)
Instructor: Yuntian Deng
Instructor Email: yuntian@uwaterloo.ca
Course Piazza: https://piazza.com/uwaterloo.ca/spring2025/cs486686
Office Hours: Thursdays 4-5pm in DC2633
Course Schedule:
- Section 001: Tuesday/Thursday 2:30PM - 3:50PM in MC 4045
- Section 002: Tuesday/Thursday 11:30AM - 12:50PM in MC 2054
First Class: May 6, 2025
Final Exam: To be announced
Quiz Due Date Update: Quiz 1 and Quiz 2 are both due on Tuesday, May 27.
Note about Quizzes: All quizzes are due two days after release date in LEARN, at 11:59pm.
Note: This is a provisional version of the syllabus. Expect changes over time.
Teaching Assistants
All TA emails end with @uwaterloo.ca
- Wentao Zhang (w564zhan) - Piazza Management
- Hala Sheta (hsheta) - Quiz Management
- Ruoxi Ning (r2ning) - Assignment 1 Management
- Bihui Jin (b27jin)
- Shuhui Zhu (s223zhu)
- Haolin Yu (h89yu)
Important: For inquiries related to a particular duty (e.g., Piazza, quizzes), please directly reach out to the corresponding TA and cc the instructor. The instructor receives many emails and response time may be slow.
Office Hours
- Bihui Jin: Monday 1-2pm in DC 2633
- Shuhui Zhu: Tuesday 1-2pm in DC 2633
- Yuntian Deng: Thursday 4-5pm in DC2633
- Haolin Yu: Friday 4-5pm in DC 2633
Communication
- All communication should take place using the Piazza discussion board.
- We do not upload materials or assignments to Piazza; these materials will appear on LEARN.
- Public Piazza posts (can be anonymous) are the preferred method for questions about course material. Students can then help each other and instructors can read/reply.
- Private Piazza posts (to instructors only) can be used for any posts that contain solution snippets or private questions.
- Only in exceptional cases where you need to contact only the instructor should you use the personal email above.
Waitlist
If you cannot register for the course, please send an email to yuntian@uwaterloo.ca to join the waitlist.
Course Description
This course provides an introduction to the field of artificial intelligence. Topics include search algorithms, game playing, knowledge representation and reasoning, uncertainty and probabilistic reasoning, machine learning, neural networks, and reinforcement learning.
Assessment
For CS486 students:
- 3 Assignments (30% - to be done individually - dates to be announced)
- 10 weekly after-class quizzes (20% - to be announced weekly)
- Two and a half hour written final examination (50% and must pass the final to pass the course)
For CS686 (grad) students:
- 3 Assignments (30% - to be done individually - dates to be announced)
- Project done individually (30%)
- Two and a half hour written final examination (40%)
Project (CS686)
- The project is meant to be finished individually.
- The project proposal deadline will be announced.
- The project can consist of a new AI algorithm, a new theoretical analysis of an existing AI algorithm, a new dataset or benchmark to evaluate existing AI algorithms, an empirical evaluation of existing AI algorithms, or a literature survey.
- The proposal should contain a 1-page description about the problem you aim to solve, including background, motivation, and proposed methods.
- The project needs to be related to the course, including search algorithms, hidden Markov models, reinforcement learning, neural networks.
- The project needs to contain the following sections: problem definition, dataset construction, algorithm design, experiments, evaluation, conclusion.
- Please use LaTeX template to write the final report.
- Please make sure the code is not copied from public repositories. Any violation will be seen as plagiarism with serious consequences.
Submission Guidelines
- Assignments are to be done individually unless otherwise stated.
- Submit assignments and receive marks through Learn.
- No late assignments will be accepted.
- Submit project proposals on LEARN before the deadline.
- Students wishing to write a project (and all CS686 students) must submit a project proposal.
Reading Materials
Primary Text:
David Poole and Alan Mackworth "Artificial Intelligence: Foundations of Computational Agents". Cambridge University Press, (2nd edition: 2017).
(Available online. Check the online resources and in particular the Python programs.)
Secondary Readings:
- Russell and Norvig "Artificial Intelligence: A Modern Approach"
- Ian Goodfellow, Yoshua Bengio, and Aaron Courville "Deep Learning"
- Richard Sutton and Andrew Barto "Reinforcement Learning: An Introduction"
Course Schedule
The exact schedule will be updated as the course progresses.
Date | Lecture | Topic | Notes |
---|---|---|---|
Search | |||
Tue, May 6 | L1 | Introduction to Artificial Intelligence | Slides |
Thu, May 8 | L2 | Uninformed Search | Slides |
Tue, May 13 | L3 | Heuristic Search | Slides, Quiz 1 (due Tue, May 27) |
Thu, May 15 | L4 | Heuristic Search (continued) | Slides |
Tue, May 20 | L5 | Constraint Satisfaction Problems | Slides |
Uncertainty Estimation | |||
Thu, May 22 | L6 | Local Search | Slides, Quiz 2 (due Tue, May 27) |
Tue, May 27 | L7 | Probabilities | Slides, Quiz 1 due, Quiz 2 due |
Thu, May 29 | L8 | Independence and Bayesian Networks I | Slides, Quiz 3 (due Tue, Jun 3), Assignment 1 Release (due Thur, Jun 12) |
Tue, Jun 3 | L9 | Independence and Bayesian Networks II | Slides, Quiz 3 due |
Thu, Jun 5 | L10 | Variable Elimination Algorithm | Slides, Quiz 4 (due Tue, Jun 10) |
Tue, Jun 10 | L11 | Hidden Markov Models I | Quiz 4 due |
Markov Decision Process | |||
Thu, Jun 12 | L12 | Hidden Markov Models II | Quiz 5 (due Tue, Jun 17), Assignment 1 Due |
Tue, Jun 17 | L13 | Decision Theory | Quiz 5 due |
Thu, Jun 19 | L14 | Markov Decision Processes I | Quiz 6 (due Tue, Jun 24), Assignment 2 Release |
Tue, Jun 24 | L15 | Markov Decision Processes II | Quiz 6 due |
Machine Learning & Deep Learning | |||
Thu, Jun 26 | L16 | Reinforcement Learning | Quiz 7 (due Tue, Jul 1) |
Tue, Jul 1 | L17 | Introduction to Machine Learning | Quiz 7 due, Project Proposal Due (CS686) |
Thu, Jul 3 | L18 | Unsupervised Learning | Quiz 8 (due Tue, Jul 8), Assignment 2 Due |
Neural Networks | |||
Tue, Jul 8 | L19 | Decision Trees | Quiz 8 due, Assignment 3 Release |
Thu, Jul 10 | L20 | Neural Networks I | Quiz 9 (due Tue, Jul 15) |
Tue, Jul 15 | L21 | Neural Networks II | Quiz 9 due |
Thu, Jul 17 | L22 | Neural Networks III | Quiz 10 (due Tue, Jul 22) |
Tue, Jul 22 | Project Presentations (CS686) | Quiz 10 due, Assignment 3 Due | |
Thu, Jul 24 | L23 | Course Recap | |
TBA | Final Exam | ||
TBA | Final Project Report Due (CS686) |
University of Waterloo Academic Integrity Policy
In order to maintain a culture of academic integrity, members of the University of Waterloo community are expected to promote honesty, trust, fairness, respect and responsibility. Check the Office of Academic Integrity's website for more information.
Grievance
A student who believes that a decision affecting some aspect of his/her university life has been unfair or unreasonable may have grounds for initiating a grievance. Read Policy 70 - Student Petitions and Grievances, Section 4. When in doubt please be certain to contact the department's administrative assistant who will provide further assistance.
Discipline
A student is expected to know what constitutes academic integrity, to avoid committing academic offenses, and to take responsibility for his/her actions. A student who is unsure whether an action constitutes an offense, or who needs help in learning how to avoid offenses (e.g., plagiarism, cheating) or about "rules" for group work/collaboration should seek guidance from the course professor, academic advisor, or the Undergraduate Associate Dean. For information on categories of offenses and types of penalties, students should refer to Policy 71-Student Discipline. For typical penalties check Guidelines for the Assessment of Penalties.
Avoiding Academic Offenses
Most students are unaware of the line between acceptable and unacceptable academic behaviour, especially when discussing assignments with classmates and using the work of other students. For information on commonly misunderstood academic offenses and how to avoid them, students should refer to the Faculty of Mathematics Cheating and Student Academic Discipline Policy.
Appeals
A decision made or a penalty imposed under Policy 70, Student Petitions and Grievances (other than a petition) or Policy 71, Student Discipline may be appealed if there is a ground. A student who believes he/she has a ground for an appeal should refer to Policy 72 - Student Appeals.
Note for students with disabilities
The AccessAbility Services Office (AAS), located in Needles Hall, Room 1401, collaborates with all academic departments to arrange appropriate accommodations for students with disabilities without compromising the academic integrity of the curriculum. If you require academic accommodations to lessen the impact of your disability, please register with the AAS at the beginning of each academic term.