CS486/686: Introduction to Artificial Intelligence


Winter 2020


People:


COVID-19 UPDATE

In-person course activities are suspended through to the end of term. Here's how we'll proceed for CS486 (subject to change, but likely to stay roughly like this)
  1. There are 3 remaining lectures (lecture10a,10b and 10c on decision theory, MDPs and RL, respectively). I will post videos of these lectures during the next week or so. You are responsible for viewing the videos and asking questions on Piazza. The video lectures are on LEARN and also here
  2. There are 2 assignments remaining. The deadlines for these do not change. Please submit your A3 by 5pm on Sunday March 15th. A4 will be released hopefully this weekend with a deadline of April 3rd. A4 is optional (see piazza post about grading)
  3. projects are still due on April 15th at 1230pm (mandatory for cs686 students, optional for cs486 students who submitted a proposal)
  4. The final exam I will have to sort out. my current thinking is a take-home final which will be more like an extended assignment. This will be likely be released on the last day of class and be due on the 15th of April. I will make a decision about this next week and let you all know. See Piazza post about updated grading scheme.
  5. my office hours will proceed as usual and I will be in DC2584 in person on Mondays at 1pm. I will make myself available during my office hours online through LEARN virtual classroom.
  6. TA office hours will be delivered online.
  7. Weights of assignments, midterm and final will be modified to account for the missing in-person final exam. I will decide how to proceed and post about this next week. See piazza post @360

Communication


Deliverables (Assignment submissions and grades)


TIMETABLE:

Lectures will take place twice per week as follows

Exams:

Office Hours are as follows:

STRUCTURE

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 four assignments, a midterm, and a final exam. Graduate students must complete a project (optional for undergraduates).


READINGS:

Primary Texts:

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

Secondary Readings:

Russell and Norvig Artificial Intelligence
Ian Goodfellow and Yoshua Bengio and Aaron Courville Deep Learning

Assessment

NOTE: DUE TO COVID19, THIS ASSESSMENT SCHEME IS NO LONGER VALID - SEE PIAZZA POST FOR NEW SCHEME

For CS486 students:

For CS686 (grad) students:

How and Where to submit


Course Objectives

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

Course Topics

  1. Agents and Abstraction
  2. States and Searching
  3. Features and Constraints
  4. Propositions and Inference
  5. Reasoning under uncertainty
  6. Supervised Learning
  7. Unsupervised Learning
  8. Reinforcement Learning
  9. Machine Learning
  10. Neural Networks and Deep Learning
  11. Planning under certainty
  12. Planning under uncertainty
  13. Additional topics if time permits
(not necessarily covered in this order)

COURSE SLIDES

The lecture slides and schedule will be finalised as the course progresses.

ASSIGNMENTS

Posted assignments with firm dates:
  1. Assignment 1 Due January 29th, 2020 at 5pm (in LEARN dropbox for assignment 1). For TA office hours see above under office hours.
  2. Assignment 2 and datasets for Q2. Due February 14th, 2020 at 5pm. (in LEARN dropbox for assignment 2). LATE ASSIGNMENTS ACCEPTED until February 18th, 2020 February 19th, 2020 at 5pm with no penalty
  3. Assignment 3 and datasets for Q2 (these are the same as for assignment 2). Due March 11th March 13th March 15th, 2020 at 5pm (in LEARN dropbox for assignment 3).
  4. Assignment 4 and dataset. Due April 3rd, 2020 at 5pm (in LEARN dropbox for assignment 4).
  5. Assessment 5. Due April 15th, 2020 at 5pm (in LEARN dropbox for Assessment 5).
Upcoming assignments with tentative dates:

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.

Academic Integrity

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.

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.