|
STA 414/2104 (Fall 2015): Statistical Methods for Machine Learning and Data Mining
Extra Office hours on Monday, Dec 14th, 1-2pm.
Instructor :
-
Russ Salakhutdinov, Office: Pratt Building, Room 290F
- Email:
rsalakhu [at] cs [dot] toronto [dot] edu
- Lectures: Mondays 2-5pm, MC 254
- Office hours: Mondays 11:00am - 12:00pm in Pratt Building, Room 290F.
Marking Scheme:
- For undergraduate students
- 3 assigments: 40%
- 2-hour midterm 20%
- 3-hour final exam 40%
- For graduate students
- 3 assigments: 40%
- 2-hour midterm 20%
- 3-hour final exam 30%
- 10% A 12-minute individual presentation on a conference paper that you have read.
In class nidterm is on Oct 26th
You can use a nonprogrammable calculator and
an 8 by 11 inch Crib Sheet - Single-sided .
Final is on Thursday, Dec 17th, RW, 110, 117, 9 - 12am.
You can use a nonprogrammable calculator and
an 8 by 11 inch Crib Sheet - Double-sided .
Course Outline:
This course covers some of the theory and methodology
of statistical aspects of machine learning. The preliminary set of
topics to be covered
include:
-
Linear methods for regression, Bayesian linear regression
- Linear models for classification
- Probabilistic Generative and
Discriminative models
-
Regularization methods
-
Model Comparison and BIC
- Neural Networks
- Radial basis function networks
- Kernel Methods, Gaussian processes, Support Vector Machines
- Mixture models and EM algorithm
- Graphical Models and Bayesian Networks
Prerequisite: Either STA302H or CSC411H
Books :
Christopher M. Bishop (2006)
Pattern Recognition and Machine Learning,
Springer.
You can also use these books for additional reference:
Contact Information
Email: rsalakhu [at] cs [dot] toronto [dot] edu
[
Home |
Assignments |
Lecture Schedule |
]
STA 414/2104 (Fall 2015): Statistical Methods for Machine Learning and Data Mining
|| http://www.cs.toronto.edu/~rsalakhu/STA414_2015/
|