This course will provide you with an understanding of a range of applications to which artificial intelligence can be applied and the ability to choose appropriate AI techniques for each. You will be able to describe key characteristics of different agent architectures and machine learning methods. Finally, through the class assignments, you will gain hands-on experience in the design and implementation of intelligent agent systems, employing a variety of AI techniques.

Students enrolling in this course should have competent programming skills (language is irrelevant) to implement computer code several hundred lines in length, be aware that the workload in this course is non-trivial, and understand that despite the disappearance of our department's policy on plagiarism, your instructor still considers cheating to be an academic offence.

AI is a 500-level course, meaning that it is available to both graduate and senior undergraduate students. Before enrolling, do keep in mind that the workload is non-trivial, in particular for students who lack fundamental skills in computer programming, as some of the assignments require up to 500 lines of code for a correct implementation (and although outside the scope of the assignment requirements, some students have gone well beyond this). (from a non-student's comment): "I do remember students who took your classes. They were clearly divided as those who complained saying that you were a hard grader and expected them to do work, and those who were appreciative for the hard work and what they learned. All those who were willing to do work thought you were a great educator." (Full disclosure: Not all students agree with that comment.)

Departmental administration has pressured the instructor either to dumb down this course (by reducing the workload) to make it more palatable to mediocre undergraduate students, or change the designation to a 600-level, and thus, restrict enrollment to graduate students, or increase the number of credits associated with the course.

I maintain that such changes would be counterproductive. Not only would they suggest that the quality of our academic program is dropping, but none of the options would be desirable to students, as I explain here:

• Reduce workload: In order to gain an understanding of the often complex algorithms that constitute much of AI, the experience of an implementation effort is demanded. Reducing workload means eliminating these programming assignments. Already, the workload in AI is less than that of my 400-level course on Human-Computer Interaction as well as that of the 400-level Operating Systems class (at least, as I remember it).
• Change to a 600-level designation: It would be unfair to exclude bright undergraduate students from the learning opportunity simply because our faculty has lowered its standards. Ironically, the top undergraduate students have usually outperformed the top graduate students in this class, despite having to deal with a heavier course load.
• Increase credits: This is the least problematic of the options, but the added value on one's transcript risks encouraging greater enrollment by borderline students who should not be taking 500-level courses in the first place. In turn, the quality of the course material would decline, and everybody loses.

Stuart Russell and Peter Norvig. Artificial Intelligence: A Modern Approach (3rd edition), Prentice Hall, 2009. This text can be purchased from various on-line stores or Paragraphe Bookstore (2220 McGill College). The text is also available on reserve in the Schulich library. The first and second editions of this text are perfectly acceptable, in particular as the authors were kind enough to provide a chapter map between the first two editions.

The course grade will be based on three assignments, each worth 15%, a group-based term project, worth 25%, and a final examination, worth 30%. Each of the assignments is designed to provide familiarity with a different aspect of artificial intelligence, while the term project, to be done in groups of 2-3 students, is intended to provide an opportunity for students to apply their overall knowledge gained through the course to a challenging, real-world problem.

Unless discussed with the instructor at least one week in advance, all assigned work is due at 11h00 on the due date. The penalty for all late submissions will be 15% if received within 24 hours, 30% if received within 48 hours of the due date; no work will be accepted thereafter.

Your instructor values it. Google my name with "academic integrity".