Machine Learning - Waseda University - Summer 2011


If you want to arrange a meeting or have any question, just send me an email  at the following address: arnaud at cs dot ubc dot ca

Prerequisites: Linear algebra, calculus, probability theory, programming (Matlab).

Textbook


I will follow primarily the following textbook:
Chris Bishop, Pattern Recognition and Machine Learning, Springer-Verlag, 2006.

I will also use some material from the book of  my UBC colleague Kevin Murphy, Machine Learning: a probabilistic approach
that will be published by MIT Press next year.

You might want to have a look at the freely available book by David Barber, Bayesian Reasoning and Machine Learning

Basics

Programming language: The programming language of the course is Matlab. I strongly recommend you follow this link and become familiar with Matlab.
Maths : If you do not feel comfortable with calculus, linear algebra and probability then please do read the following material

* Cribsheet
* Linear algebra: A review Another review
* Probability: Probability theory refresher, another review

Potential projects here

Acknowledgments

I will reuse some of the material developed by my UBC colleagues Nando de Freitas and Kevin Murphy.


Announcements


Handouts

* 20th June: I've corrected in the slides
- page 7 and page 8, definition of the matrix Phi (I was starting numeroting the columns from index 0 instead of 1)
- page 21: definition of the prior p(w). You have (beta*lambda)^-1 appearing instead of  (beta*lambda)
- page 32: reformatted the text so that it is not cut anymore!

Reading: Chapter 3 of the book of Bishop.

 Reading: Chapter 6 of the book of Bishop.
Additional reading:  Introduction to Gaussian processes

Reading: Chapter 11 of the book of Bishop
You can also read An introduction to MCMC for machine learning Pdf file

Reading: An introduction to SMC