| |
CSC2515 Fall 2008 - Lectures
Lecture Schedule:
Some of the later lectures do not yet exist and their titles may change.
The final version of each
lecture and the final version of the readings for that lecture
will be posted on or before
the day of the lecture.
The first lecture starts at 1.00pm
- September 10
Lecture 1: Overview of Machine Learning
(notes as .ppt )
(notes for all browsers))
(notes as .ps, 4 per page))
Reading: Chapter 1, pp 1-48.
Tutorial 1: (3.00-4.00) The Gaussian Distribution
Reading: Chapter 2, pp 78-94
- September 17
Lecture 2: Linear Regression
(notes as .ppt )
(notes for all browsers))
(notes as .ps, 4 per page))
Reading: Chapter 3, pp 137-173
Tutorial 2: (3.00-4.00) Distributions for binary and multinomial variables; The exponential family.
Reading: Chapter 2, pp 67-78; 113-120.
- September 24
Lecture 3: Linear Classification
(notes as .ppt )
(notes for all browsers))
(notes as .ps, 4 per page))
Reading: Chapter 4: pp 179-210
Tutorial 3: (3.00-4.00) Worked examples using the material covered so far.
- October 1 Assignment 1 posted on web
Lecture 4: Neural Networks trained by Backpropagation
(notes as .ppt )
(notes for all browsers))
(notes as .ps, 4 per page))
Reading: Chapter 5: 225-249, 256-269
Tutorial 4: (3.00-4.00) Introduction to assignment followed by help with Matlab for novice users.
pdf slides
of Matlab tutorial.
- October 8 Assignment 1 due at start of lecture
Lecture 5: Clustering and Mixture Models
(notes as .ppt )
(notes for all browsers))
(notes as .ps, 4 per page))
Tutorial 5: (3.00-4.00)
Reading: Chapter 2: 120-127; Chapter 9: Pages 423-455; Chapter 5:269-272
- October 15
Assignment 2 posted on web
Lecture 6: Decision Trees and Mixtures of Experts
(notes as .ppt )
(notes for all browsers))
(notes as .ps, 4 per page))
Readings: Chapter 5: 272-277
Mixture of
Experts paper
Hierarchical Mixture of
Experts paper
Tutorial 6: 3.00-4.00 Conjugate gradient optimization and introduction to assignment 2.
Tutorial slides
Reading for tutorial:
Conjugate
gradient paper
- October 22 One page project proposal due (see
projects page)
Assignment 2 due at start of lecture
Lecture 7: Continuous Latent Variable Models
(Lecture 7 (part 1) as .ppt )
(Lecture 7 (part 1) as .htm))
(Lecture 7 (part 1) as .ps)
(Lecture 7 (part 2) as .pdf)
(Lecture 7 (part 3) as .ppt )
(Lecture 7 (part 3) as .htm))
(Lecture 7 (part 3) as .ps)
Reading: Chapter 12 excluding pages 586-590
Tutorial 7: Matrix factorization methods for collaborative filtering.
Tutorial on Probabilistic Matrix Factorization
- October 29 Assignment 3 posted on web
Lecture 8: Deep Belief Nets
(notes as .ppt )
(notes
as .htm))
(notes
as .ps, 4 per page))
Readings:
Simple introduction to Boltzmann machines
The first paper on deep learning
Optional Reading List
- November 5 The due date for assignment 3 is now Nov 12
Lecture 9: Time-series Models
(notes for part 1 as .pdf )
(notes for part 2 as .ppt)
(notes for part 2 as .ps, 4 per page))
Reading for first part of lecture: Chapter 13 pages 605-643
Reading for second part of lecture:
(.pdf short paper on using RBM's to model
motion capture data )
Tutorial 9: Restricted Boltzmann machines for collaborative filtering.
- November 12 Assignment 3 now due at start of lecture
Lecture 10a: Nearest Neighbor and Kernel Density
(notes as .ppt )
(notes for all browsers))
(notes as .ps, 4 per page))
Reading: Chapter 2: pages 120-127.
Lecture 10: Support Vector Machines
(notes as .ppt )
(notes for all browsers))
(notes as .ps, 4 per page))
Reading: Chapter 7: pages 325-345.
- November 19 :
Lecture 11: Applications
of machine learning to language modeling and to retrieval of documents
and images.
notes on language modeling as .pdf
notes on document retrieval as .pdf
Reading: Semantic hashing paper
Tutorial 11: Boosting and Naive Bayes
(Boosting notes as .ppt )
(Boosting notes for all browsers))
(Boosting notes as .ps, 4 per page))
Naive Bayes
- November 26
Lecture 12: Gaussian Processes
notes as .pdf
Reading: Chapter 6 pages 303-315
Tutorial 12: The tutorial time will be used to allow people to ask
questions about anything in the course. Its a good time to sort out
things you dont understand before the final test.
- December 3 Final test from 1.10-2.40
information about the test as .ppt
Reading:
- Friday December 19 Projects due by noon
Email .pdf or .ps file to csc2515prof@cs.toronto.edu
|