CS486/686: Introduction to Artificial Intelligence
The final exam for CS486/686 will be on April 17th from 12:30pm-3:00pm in PAC 7,8
- Dr. Jesse Hoey, (jhoey [at] cs [dot] uwaterloo [dot] ca)
- Aravind Balakrishnan (TA)
- Ashish Gaurav (TA)
- Milad Khaki (TA)
- Sajin Sasy (TA)
- Pan Pan Chen (TA)
- Timmy Rong Tian Tse (TA)
- All communication should take place using the
Piazza discussion board
- Sign up for Piazza (if you're not already) here
- Public Piazza posts (can be anonymous) are the preferred method for questions about course material, etc. 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.
Deliverables (Assignment submissions and grades)
- Assignments and grades will be handled through Learn
- If you are not familiar with Learn, see the instructions for using dropboxes to hand in assignments.
Lectures will take place twice per week as follows
Office Hours are as follows:
- Section 002: Monday/Wednesday 1000-1120hrs (10:00am-11:20am in RCH309)
- Section 001: Monday/Wednesday 1300-1420hrs (1:00pm-2:20pm in RCH307)
- Jesse Hoey: Thursday 3pm-4pm in DC2584 (Computational Health Informatics Laboraty)
- TAs will hold special office hours for each assignment
- Assignment 1 office hours:
- Friday Jan 26th 2-3pm (Sajin Sasy) DC2568 (Seminar room)
- Monday Jan 29th 2-4pm (Timmy Tse) in DC2306C (AI Lab meeting room)
- Assignment 2 office hours:
- Wednesday Feb 14th 12-1:30pm (Milad Khaki) in DC2306C (AI Lab meeting room)
- Friday Feb 16th 2:00-3:30pm (Milad Khaki) in DC2568 (Seminar room)
- Assignment 3 office hours:
- Wednesday March 7th 4:30-5:30pm (Milad Khaki) in DC2306C (AI Lab meeting room)
- Friday March 9th 1:30-2:30pm (Milad Khaki) in DC2306C (AI Lab meeting room)
- Assignment 4 office hours:
- Tuesday March 27th 10:30am-12:30pm (Ashish Gaurav/Aravind Balakrishnan) in DC2368 (Seminar Room)
- Wednesday March 28th 10:30am-12:30pm (Ashish Gaurav/Aravind Balakrishnan) in DC2368 (Seminar Room)
The course will consist of two 1.5-hour in-class sessions per week.
The course content will be delivered in a lecture format, with five assignments and a final exam.
Graduate students must complete a project (optional for undergraduates).
David Poole and Alan Mackworth "Artificial Intelligence: Foundations of Computational Agents". Cambridge University Press, (1st edition: 2010, 2nd edition: 2017).
(available online. The section references below are to the 2nd edition.)
And the useful and informative java applets on the CI-Space website
Russell and Norvig Artificial Intelligence
Ian Goodfellow and Yoshua Bengio and Aaron Courville Deep Learning
For CS486 students:
- Assignments (5) (60% - to be done individually - due at 12pm - dates to be announced)
- Two and a half hour written examination (April 17th 1230pm-300pm) (40% and must pass the final to pass the course)
- Optional project (5% bonus) (see here for details)
For CS686 (grad) students:
- Assignments (5) (35% - to be done individually - due at 12pm - see the schedule above for the tentative dates)
- Two and a half hour written examination (April 17th 1230pm-300pm) (35%)
- Project (30%) (see here for details)
How and Where to submit
- Assignments are to be done individually unless otherwise stated
- Submit assignments and receive marks through Learn.
- If you are not familiar with Learn, see the instructions for using dropboxes to hand in assignments.
- No late assignments will be accepted
- Submit project proposals to the instructor in class on Valentine's Day (Feb 14th)
- Submit final projects to the instructor at the final exam
The design of automated systems capable of accomplishing complicated tasks is at the heart of computer science. Abstractly, automated systems can be viewed as taking inputs and producing outputs towards the realization of some objectives. In practice, the design of systems that produce the best possible outputs can be quite challenging when the choice of outputs is constrained, the consequences of the outputs are uncertain and/or dependent on other systems, the information provided by the inputs is incomplete and/or noisy, there are multiple (possibly competing) objectives to satisfy, the system must adapt to its environment over time, etc. This course provides an introduction to Artificial Intelligence, covering some of the core topics that underly automated reasoning. The modeling techniques that will be covered are quite versatile and can be used to tackle a wide range of problems in many fields including natural language processing (e.g., topic modeling, document clustering), robotics (e.g., mobile robot navigation), automated diagnosis (e.g., medical diagnosis, fault detection), data mining (e.g., fraud detection, information retrieval), operations research (e.g., resource allocation, maintenance scheduling), assistive technologies, human-computer interaction, etc.
See the official official course outline
(not necessarily covered in this order)
- Agents and Abstraction
- States and Searching
- Features and Constraints
- Propositions and Inference
- Reasoning under uncertainty
- Supervised Learning
- Unsupervised Learning
- Reinforcement Learning
- Machine Learning
- Neural Networks and Deep Learning
- Planning under certainty
- Planning under uncertainty
- Additional topics if time permits
The lecture slides and schedule will be finalised as the course progresses.
- January 3rd, 2018: Introduction Slides (88kb) (6-up version (118Kb) )
Readings: Poole and Mackworth (2nd Ed.) 1.1
- January 8th, 2018: What is AI? Slides (45Mb) (6-up version (21Mb))
Readings: Poole and Mackworth (2nd Ed.) 1.1-1.2
- January 10th, 2018: Agents and Abstraction Slides (77Mb) (6-up version (33Mb))
Readings: Poole and Mackworth (2nd Ed.) 1.3-1.10, 2.1-2.3
- January 15th, 2018: States and Searching Slides (1Mb) (6-up version (1.7Mb))
Readings: Poole and Mackworth (2nd Ed.) Chapt. 3 (all)
- January 17th, 2018: Features and Constraints Slides (0.5Mb) (6-up version (1.1Mb))
Readings: Poole and Mackworth (2nd Ed.) Chapt. 4.1-4.8
- January 24th, 2018: Propositions and Inference Slides (0.4Mb) (6-up version (1.5Mb))
Readings: Poole and Mackworth (2nd Ed.) Chapt. 5.1-5.3, and Chapt. 13.1-13.2
- January 29th, 2018: Planning under certainty Slides (0.2Mb) (6-up version (1.5Mb))
Readings: Poole and Mackworth (2nd Ed.) Chapt. 6.1-6.4
- January 31st, 2018: Supervised Learning I Slides (0.4Mb) (6-up version (1 Mb))
Readings: Poole and Mackworth (2nd Ed.) Chapt. 7.1-7.3.1,7.4
- February 5th, 2018: Supervised Learning II Slides (0.5Mb) (6-up version (1 Mb))
Readings: Poole and Mackworth (2nd Ed.) Chapt. 7.3.2,7.5-7.6
- February 7th, 2018: Reasoning under Uncertainty I Slides (1.5Mb) (6-up version (2.4 Mb))
Readings: Poole and Mackworth (2nd Ed.) Chapt. 8.1-8.4
- February 14th, 2018: Reasoning under Uncertainty II Slides (0.75Mb) (6-up version (1.25 Mb))
Readings: Poole and Mackworth (2nd Ed.) Chapt. 8.5-8.9
- February 28th, 2018: Learning with Uncertainty I Slides (0.25Mb) (6-up version (0.55 Mb))
Readings: Poole and Mackworth (2nd Ed.) Chapt. 10.1,10.4
- March 5th, 2018: Learning with Uncertainty II Slides (0.20Mb) (6-up version (0.41 Mb))
Readings: Poole and Mackworth (2nd Ed.) Chapt. 10.2,10.3,10.5
- March 7th, 2018: Planning under Uncertainty I Slides (0.31Mb) (6-up version (0.71 Mb))
Readings: Poole and Mackworth (2nd Ed.) Chapt. 9.1-9.3
- March 14th, 2018: Planning under Uncertainty II Slides (0.84Mb) (6-up version (1.75Mb))
Readings: Poole and Mackworth (2nd Ed.) Chapt. 9.5
- March 21st, 2018: Planning under Uncertainty III Slides (3.3Mb) (6-up version (4.1 Mb))
Readings: Poole and Mackworth (2nd Ed.) Chapt. 12.1,12.3-12.9
- March 26th, 2018: Affective Computing and Social Dilemmas Slides (8.6Mb) (6-up version (9 Mb))
Posted assignments with firm dates:
- Assignment 1 Due January 30th, 2018 at 5pm (in LEARN dropbox for assignment 1). For TA office hours see above under office hours.
- Assignment 2 and datasets for Q2. Due February 20th, 2018 at 5pm. (in LEARN dropbox for assignment 2).
- Assignment 3 and datasets for Q2 (these are the same as for assignment 2). Due March 12th, 2018 at 5pm (in LEARN dropbox for assignment 3).
- Assignment 4 and data+code. Due March 29th, 2018 at 5pm (in LEARN dropbox for assignment 4).
- Assignment 5 and simulation code. Due April 4th, 2018 at 5pm (in LEARN dropbox for assignment 5. Late assignments will be accepted until April 10th, 2018, 5pm).
OTHER MATERIAL (videos, software, handouts, etc)
University of Waterloo Academic Integrity Policy
The University of Waterloo Senate Undergraduate Council has also approved the following message outlining University of Waterloo policy on academic integrity and associated policies.
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.
All members of the UW community are expected to hold to the highest standard of academic integrity in their studies, teaching, and research. This site explains why academic integrity is important and how students can avoid academic misconduct. It also identifies resources available on campus for students and faculty to help achieve academic integrity in, and our, of the classroom.
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.
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.
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 Office for Persons with Disabilities (OPD), located in Needles Hall, Room 1132, 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 OPD at the beginning of each academic term.