# Stat406 (Algorithms for classification and prediction) Spring 2010 (term 2)

MWF 1-2, Math 225, Lab W 4-5 LSK 302.

Final exam: Apr 22, 8:30-11am am, MATH 103

Grading: midterm 35%, final 40%, homewokrs 25%.

Synoposis: This is a senior-level undergraduate class on machine learning, covering the foundations, such as (Bayesian) statistics and information theory, and then focusing on supervised learning (classification, regression).

Textbook: Draft copies of my textbook, Machine Learning: a probabilistic approach, will be made available for purchase on Jan 2nd, 2010, for \$56.50, from CopieSmart in the UBC Village, between MacDonald's and the food court.

Abbreviated version for final exam is here

Pre-requisites. Linear algebra, calculus, probability theory, programming (preferably R or Matlab), some previous class on machine learning (eg CS 340) or applied statistics (eg Stat 306).

TA: Pavel Krupski p.krupskii@stat.ubc.ca

TA office hours: Tue 11-12, 312 LSK

Instructor Office hours: Fri 2-3, Stat 308d, or by appointment

If you are registered, please join google groups which will be used for class-related announcements and discussions.

# Timetable

In the table below, reading refers to sections from my textbook. (Sections in brackets are optional reading; they will not be on the exam, but may be of interest.) Handouts are more recent versions of my book chapters.
L# Date Topic Reading Homework
L1 Mon Jan 4
Admin, quiz . hw1.pdf, due Mon 11th. See also Getting started in Matlab for help.
L2 Wed Jan 6
Quiz postmortem, classification 1.1.1 .
L3 Fri Jan 8
KNN classifiers, cross validation 1.4.2.1 .
L4 Mon Jan 11
Linear regression 1.1.3- 1.1.4, 11.3 .
L5 Wed Jan 13
Linear regression cont'd 11.3 hw2.pdf, due Wed 20th
L6 Fri Jan 15
Ridge regression 11.4-11.5 .
L7 Mon Jan 18
Robust regression 11.6, robust regression handout .
L8 Wed Jan 20
Logistic regression 12.1-12.2 hw3, due wed 27. spamData.mat
L9 Fri Jan 22
Log. reg. cont'd 12.3, logistic regression handout .
L10 Mon Jan 25
Neural nets 14.1 .
L11 Wed Jan 27
Neural nets 14.2, Neural nets handout .
L12 Fri Jan 29
Naive Bayes classifiers Generative classifiers handout. hw4,due Fri Feb 5
L13 Mon Feb 1
Naive Bayes classifiers . .
L14 Wed Feb 3
Discriminant analysis . .
L15 Fri Feb 5
Discriminant analysis Regularized discriminant analysis hw5,due Fri Feb 2
L16 Mon Feb 8
Mixture models Mixture models (5feb2010 version) .
L17 Wed Feb 10
Mixture models . .
L18 Fri Feb 12
Mixture models . .
L19 Mon Feb 15
olympics . .
L20 Wed Feb 17
olympics . .
L21 Fri Feb 19
olympics . .
L22 Mon Feb 22
olympics . .
L23 Wed Feb 24
olympics . .
L24 Fri Feb 26
olympics . .
L25 Mon Mar 1
Review Shortened edition 19feb10 version of book, only contains topics for the midterm (you can ignore starred sections) .
L26 Wed Mar 3
. . .
L27 Fri Mar 5
Midterm . .
L28 Mon Mar 8
L1 regularization sec 4.4 (19feb) .
L29 Wed Mar 10
L1 regularization sec 4.4 (19feb) .
L30 Fri Mar 12
Sparse Kernel machines Sparse kernel machines handout hw6,due Mon 22
L31 Mon Mar 15
Kernel machines . .
L32 Wed Mar 17
Kernel machines Updated Sparse kernel machines handout .
L33 Fri Mar 19
No class . .
L34 Mon Mar 22
Inference in Gaussian models Gaussian handout .
L35 Wed Mar 24
Linear Gaussian systems . .
L36 Fri Mar 26
Number game, Beta-Binomial model Bayesian stats 1 handout .
L37 Mon Mar 29
Summarizing posteriors . .
L38 Wed Mar 31
Bayesian hypothesis testing . hw7,due Wed 7th
L39 Fri Apr 2
Good Friday . .
L40 Mon Apr 5
Easter Monday . .
L41 Wed Apr 7
Bayesian inference for Gaussians Bayesian stats 1 handout (7 apr version), Bayesian stats 2 handout (7 apr version) hw8, due Wed 14th
L42 Fri Apr 9
Bayesian inference for linear and logistic regression Bayes2 handout .
L43 Mon Apr 12
Decision theory Ch 10 of 2jan10 version .
L44 Wed Apr 14
Review session . .