CSC321 Spring 2016
Introduction to Neural Networks and Machine Learning
University of Toronto Mississauga
Look here at least once a
week for news about the course.
Announcements:
The
final exam and midterm will be based, in part, on
the homework assignments and will assume that you
have completed them by yourselves. More generally, you are responsible for all material
covered in class, in tutorials, in the readings and
on the assignments (except as described below). However, you will not be required to
write any Matlab code, and you are not responsible for
historical facts mentioned in class or on the slides
(or anywhere else).
The final exam will have five questions. One question
will be on lecture 11, one will be on lecture 12, and
the remaining three will be from the rest of the
course. There will be no questions on Lectures 7 and
15.
Like midterm test, the final
exam will follow the "I don't know" policy: if you
leave a question (or part) blank and write "I don't
know", you will receive 20% of the marks for that
question (pr part). Otherwise, if you get the answer
wrong, you may receive 0 marks.
The final exam will be closed book. You may
bring a 1page doublesided cheat sheet on Lettersize (8.5x11in) paper with no
more than 12,000 characters (6,000 per side). If
typed, it must be in 12pt font or larger. No other
aids are allowed.
Assignment 4 is now available. It is due on Friday
April 1 at 11pm.
The slides for
Lecture 14 have been updated.
Lecture 13 has been replaced by Lecture 14.
Assignment 3 is now available on the Assignments page.
For the midterm, you will be responsible for all
material covered in class, the homework assignments
and the tutorials up until February 25 (except for the
lecture on clustering and mixtures of Gaussians). You
will not be responsible for historical facts
mentioned in class or on the lecture slides (or
anywhere else), and you will not be required
to write any Matlab code.
Broken links to lecture slides have been fixed.
Some slides have
been added to the lecture on Clustering (right after
Lecture 10).
The midterm test will follow
the "I don't know" policy: if you leave a question (or
part) blank and write "I don't know", you will receive
20% of the marks for that question (or part).
Otherwise, if you get the answer wrong, you may
receive 0 marks.
Marked
Assignment 1s are now available on UTORSubmit.
Assignment 2 is now
available (see the Assignments page).
The midterm test
will be on Friday February 26 in tutorial. It will
start at 1:10pm sharp and will last 50 minutes.
The midterm test will be closed book. You may
bring a 1page singlesided cheat sheet on Lettersize (8.5x11in) paper with no
more than 6000 characters. If typed, it must be in
12pt font or larger.
Lectures 7, 9 and
10 have been reordered. (Lecture 7 now comes after
Lectures 9 and 10.)
Assignment 1 is now a available
(see the Assignments page).
Readings have been added to
the lecture schedule.
The first tutorial
will be on Frday January 15.
Course Information
sheet: click here.
Lectures: Wednesdays
35pm in IB 335
First lecture January 6; Last lecture March 30; No
lecture on February 17 (reading week)
Click here for a list of
all the lectures (subject to change).
Tutorials:
Fridays 12pm in
CC 2130
First
tutorial: January 15
Click here for more
tutorial information.
Instructor:
Anthony Bonner
email: [my last name]
[at] cs [dot] toronto [dot] edu
Office: DH 3090 (UTM), BA
4268 (St George)
Phone: 9058283813 (UTM),
4169787441 (St George)
Office Hours: Wednesdays 56pm
Teaching Assistant: Hamed
Heydari
email: h [dot] heydari [at] mail [dot] utoronto
[dot] ca
Prerequisites:
informally: calculus, linear algebra, statistics
and computer programming
formally: CSC207H5/270H5, 290H5; MAT223H5/248Y5;
STA257H5
Marking Scheme:
Closed book Midterm test worth 20%
Closed book Final exam worth 40%
Four assignments worth 10% each
On all work, 20% of the mark will be for quality of
presentation, including the use of good English. The
final exam and midterm will be based in part on the
assignments and will assume that you have completed
them by yourself. Final marks may be adjusted up or
down to conform with University of Toronto grading
policies. Late assignments will not be accepted.
Computing: The assignments
will all be done in Matlab, but prior knowledge of
Matlab is not required. Basic Matlab will be taught
during the first tutorials.
Readings: There is no
required textbook for the class. There will be
occasional required readings which will be made
available on the web (see Lectures
and Readings). You may also find the following
books and resources useful:
Plagiarism and
Cheating:
Honesty and fairness are fundmental to the
Univrrsity of Toronto's mission. Plagiarism is a
form of academic fraud and is treated very
seriously. The work that you submit must be your own
and cannot contain anyone else's work or ideas
without proper attribution. You are expected to read
the handout How
Not to Plagiarize and to be familiar
with the Code
of Behaviour on Academic Matters, which is
linked from the UTM calendar under the link Codes and
Policies. The following website may also be helpful: Advice on
academic offences.
