NUIM CS401 F2006

Mon 12:00-12:50 CS2
Tue 15:00-15:50 JohnHume6
Instructor: Barak A. Pearlmutter, barak@cs.nuim.ie
Office: Hamilton Institute (NUIM, Rye Hall, South Wing, room 5)
Office hours: you are welcome any time, just drop on by. (Afternoons are best, excepting Fridays.) Or feel free to email or ring me up (x6394) and make an appointment. If people would prefer that I set aside some particular weekly times, let me know and I will do so.

Text

We will use notes made available on the web.

Lectures

  1. (18-Sep-2005) Introduction to Machine Learning, pre-requisites

  2. (19-Sep-2005) Introduction to R (see NOTES.R)

  3. (25-Sep-2005) Misc Definitions, and Intro to Linear Classifiers, ie Perceptron (notes)

  4. (26-Sep-2005) The Perceptron Learning Rule. The "homogeneous coordinates" trick (notes)

  5. (2-Oct-2005) Linear regression, gradient descent

  6. (3-Oct-2005) More gradient descent Backpropagation (part 1 of 2)

  7. (9-Oct-2005) Backpropagation or reverse-mode AD (part 2 of 2)

  8. (10-Oct-2005) Convergence of vanilla gradient descent of a linear unit with quadratic error

  9. (16-Oct-2005) Generalisation Curves

  10. (17-Oct-2005) Example of unsupervised learning: k-means clustering

  11. (23-Oct-2005) Maximum Likelihood Estimation: definition and toy examples (coin, Gaussian)

  12. (24-Oct-2005) EM of a simple Gaussian mixture model

  13. (6-Nov-2005) Hidden Markov Models or HMMs (1/3)

  14. (7-Nov-2005) Hidden Markov Models or HMMs (2/3)

  15. (13-Nov-2005) Hidden Markov Models or HMMs (3/3)

  16. (14-Nov-2005) graphical models: intuitions (1/2)

  17. (20-Nov-2005) graphical models: Energy, Boltzmann distributions, Monte-Carlo (2/2)

  18. (21-Nov-2005) Support Vector Machines I:

  19. (27-Nov-2005) Support Vector Machines II:

  20. (4-Dec-2005) Multiplicative updates

  21. (5-Dec-2005) Boosting (notes)

  22. (11-Dec-2005) Reinforcement Learning. Policy-value iteration, Q-learning, TD (notes)

  23. (12-Dec-2005) Case Studies: ALVINN, PAPnet, TDNN for E-set, handwritten digit recognition, TDgammon

Useful Materials

Author's lecture notes from Machine Learning by Tom Mitchell.

Code written in class, usually scrubbed up a bit.

Other Notes