CSC384: Introduction to Artificial Intelligence (Winter 2015)


(Apr. 5 )Office Hours Location & Assignment Remark Form
Office hours location: Tutorial room (DH2020)
Assignment 2 remark form.
(Apr. 3 ) Exam Period: Office Hours Schedule
Next week, we will have office hours from April 6-April 9. See detailed schedule as follows:
Instructor office hours:
April 9, Thursday: 4:30-6:30
TA office hours:
April 6, Monday: 3 - 5
April 7, Tuesday: 2 - 4
April 8, Wednesday: 2- 4
April 9, Thursday: 2 - 4
Location will be announced soon.
(Mar. 29) Revised course work evaluation scheme
A3 is officially cancelled. Scale the rest of coursework from total of 85% up to 100%.
(Mar. 29) Reminder: March 30 make-up session: 6-7:30(correction!)
1. Course work evaluation scheme revision vote!
2. Final review session.
(Mar. 24) Assignment 3 is out!
(Mar. 16) Reminder!
Tutorial sessions are cancelled for now due to the strike, until further notice. During the tutorial time, you are expected to review last week's course material and read the text book chapters 13 & 14.
(Mar. 5) Assignment 2
1. Assignment 2 and speedy solver extended to March 13 noon deadline. If you would like to be marked for your regular submission on Assignment 2 (not including speedy solver) on March 6, send me an email, and you will be given 3 bonus marks.
2. On March 30, there will be no tutorial session. Instead, I will give a final review session at 6-7:30.
(Mar. 1) Schedule Update
1. Class schedule remains normal!
2. Tutorials for this week will be cancelled. During the tutorial time, you are expected to work on your assignment 2 on your own. Follow the submission deadline.
Have fun on your Sudoku!
(Feb. 25) Office hour for this week will be on Friday 12-2 at DH 3097C.
(Feb. 23) Midterm review is posted (see below).
(Feb. 20)
1. The final exam information has been posted, see here.
2. Next Monday, both tutorial sessions will be combined and be given at the same time from 6 sharp - 7:30 as 1.5 hour lecture. I will give a review for the midterm test and finish the second half of knowledge representation.
3. Assignment 2's due date is March 6. If you want to compete for speedy Sudoku solver, submit a separate file named as speedy.txt. In this file, give clear command instructions how your solver will be run, with clearly specified algorithm. Only those who submitted for competition will be considered for the bonus points.
(Feb. 14) Assignment 2 is posted (see below). Have fun!

(Jan. 30) Assignment 1 due is coming. Please make sure you submit your files on time: searchAgents.py search.py Also, submit an electronic version of your report "report.pdf" on MarkUS! (NEW) (No penalty for report.pdf late online submission until Sunday noon.)

(Jan. 29) Your TA for the course is Andy Chow.

(Jan. 17) Assignment 1 is posted (see below).

(Jan. 15) Note-taker volunteer needed! See flyer.

(Jan. 10) There will be no tutorial on Monday January 12. The first tutorial will be on January 19.

(Jan. 9) Course starts!

(Jan. 5): Piazza is ready!
Enrol yourself in your class discussion site: http://piazza.com/utm.utoronto.ca/spring2015/csc384
The access code is csc384.

(Jan. 5): Winter 2015 course information sheet is available! READ!


[Lisa] Jing Yan
Office: DH-3097C
Email: lyan at cs.toronto.edu

Class Information

LEC0101 F 3-5pm DV1142
TUT0101 M 5-6pm DH2020 / TUT0102 M 6-7pm DH2020

Office Hours

Friday 5-7pm DH-3097C / DV1142 (after class), or by appointment

Course website

Lecture slides will be posted on weekly basis**.

** All announcements will be made through the course web page and it is your responsibility to visit it frequently.

Course Materials

Recommended Textbook:
Artificial Intelligence: A Modern Approach
Russell & Norvig, 3rd Ed., Prentice Hall, 2009


Syllabus tentative topics


Assignment late policy & re-marks

The penalty is 15% of the assignment total grade (which is 15% of the total marks), for each day to a maximum of 3 days, except for documented unusual circumstances.
If you feel a piece of your work has been graded unfairly, please submit a written re-mark form within a week of receiving the work back.

Email policy

Contact TA for questions related to assignments, instructor for other things. Please put 384 in the subject line.
Email response may be 24 hrs or longer; if you do not hear back as your expectation, come to the weekly office hour.


Plagiarism—or simply, cheating—is taken to be the handing in of work not substantially the student’s own. It is usually done without reference, but is unacceptable even in the guise of acknowledged copying. It is reprehensible, and the penalty will be severe.

It is not cheating, however, to discuss ideas and approaches to a problem, nor is it cheating to seek or accept help with a program or with writing a paper. Indeed, a moderate form of collaboration is encouraged as a useful part of any educational process. Nevertheless, good judgment must be used, and students are expected to present the results of their own thinking and writing. Never copy another student’s work—it is plagiarism to do so, even if the other student “explains it to you first.” Never give your written work to others. Sharing work with others for the purposes of plagiarism is also a violation. Do not work together to form a collective solution, from which the members of the group copy out the final solution. Rather, walk away and recreate your own solution later. If you are really stuck on a problem, don’t panic...just come and talk to the instructor or one of the TAs. For details on the meaning of plagiarism and how it is dealt with at this university, see:

Important Administrative Dates

Lecture Notes

Week of Lecture
Jan. 09 Course 00
Chapter 1: Intro
Chapter 2: Agents
Turing paper
Jan. 16 Chapter 3 Search: uninformed search
Jan. 23 Chapter 3 Search: heuristic search(updated)
Jan. 30 Chapter 6 Search: constraint satisfaction problem(backtrack search)
Feb. 6 Chapter 5 Games
Feb. 13 Knowledge Representation
Feb. 20 Reading Week
Feb. 23 Midterm Review
Mar. 6 Knowledge Representation
Mar. 13 Uncertainty
Mar. 20 Learning
Practice for BN inference computation
Mar. 27 Learning: deep learning applications
Mar. 30 Final Review


Assignment 1: Pacman Search
In this assignment, your Pacman agent will find paths through his maze world, both to reach a particular location and to collect food efficiently. You will build general search algorithms and apply them to Pacman scenarios.
You can download all the code and supporting files as a zip archive here!
Assignment 2: Sudoku Solver
This assignment will require you to develop a Sudoku solver by applying search algorithms with heuristics to solve a puzzle.
Assignment 3: Classification & Inference
This assignment will require you to build up a classifer and implement an inference component on BN. The classification task might be more challenging than it apears to be. Simple task but not easy to achieve good performance. Prize for the classificiation task will be announced later!
Data and sample provided:
Train: train.csv
Test: test.csv
Output submission:sampleoutput.csv