|
|
|
| All downloadable documents are Adobe Acrobat PDF documents. You can obtain Acrobat for free by following the link from the Adobe Icon.
|
| Date
|
Topic
|
Assignments
| |
Aug. 25
| Linear Algebra Refresher
| Handout
| |
Aug. 27
| Statistics Refresher
| Lecture Notes
| |
Sept. 3
| Issues in Neural Networks and Statistical Learning
| Bishop, Ch.1, Bias-Variance Tradeoff Derivation
| |
Sept. 8
| Introduction to Graphical Models
| Bishop, Ch.8.1 and 8.2
| |
Sept. 10
| Supervised Learning: Linear Models for Regression
| Bishop, Ch.3
| |
Sept. 15
| Supervised Learning: Kernel Methods for Regression
| Bishop, Ch.6
| |
Sept. 22
| Supervised Learning: Gaussian Process Regression
| Bishop, Ch.6
| |
Sept. 24
| The Bayesian approach to statistical learning
| Bishop, Ch.2.3.6 and 3.4
| |
Oct. 1
| Supervised Learning: Linear classification -- Part 1
| Bishop, Ch.4
| |
Oct. 6
|
| Homework 1
| |
Oct. 8
| The EM Algorithm and Variational Bayes -- Part 1,
Jo-Anne's slides (pdf),
Jo-Anne's slides (ppt, with animations)
| Bishop, Ch.9.4 and 10.1
| |
Oct. 13
| The EM Algorithm and Variational Bayes -- Part 2
| Bishop, Ch.9.4 and 10.1
| |
Oct. 15
| Supervised Learning: Linear classification -- Part 2
| Bishop, Ch.4
| |
Oct. 20
| Unsupervised Learning: Clustering and Mixture Models
| Bishop, Ch.9
| |
Oct. 22
| Mixture of Experts
| Bishop, Ch.14.5
| |
Oct. 27
| Nonparametric Methods for Density Estimation and Classification
| Bishop, Ch.2.5 and 2.6, Handout
| |
Oct. 29
| Nonparametric Methods for Regression
| Bishop, Ch.2.5, 2.6, 6.3.1 Handout
| |
Nov. 3
| Dimensionality Reduction - Part1
| Bishop, Ch.12, Homework 2
| |
Nov. 5
| Dimensionality Reduction - Part2
| Bishop, Ch.12
| |
Nov. 10
| Independent Component Analysis
| Bishop, Ch.12, Handout
| |
Nov. 12
| Support Vector Machines
| Bishop, Ch.7
| |
Nov. 17
| Bayesian Complexity Control and Sparsity
| Bishop, Ch.7
| |
Nov. 19
| Associative Memory, Hopfield Nets, Boltzmann Machines
| Handout,Homework 3
| |
Nov. 24
| Helmholtz Machines
| Handout1& Handout2
| |
Nov. 26
| Classical Neural Network Algorithms
| Homework 4
| |
Dec. 1
| Project Presentations (allow some extra time)
|
| |
Dec. 3
| Final Quiz
|
|
Outdated Course Handouts based on Bishop 1995 book:
|
Sept. 7
| Supervised Learning: Single Layer Regression
| Bishop, Ch.3
| |
Sept. 12
| Supervised Learning: Multiple Layer Networks
| Bishop, Ch.4
| |
Sept. 14
| Supervised Learning: Spatially Localized Systems
| Bishop, Ch.5
| |
Sept. 19
| Forward & Inverse Models, Distal Teachers
|
Handout
Homework 1
| |
Sept. 21
| Unsupervised Learning: PCA and Autoencoders
| Handout
| |
Sept. 26
|
Unsupervised Learning: Cluster Analysis and Density Estimation
| Bishop, Ch.2
| |
Sept. 28
| Learning and Generalization
| Bishop, Ch.9
| |
Oct. 3
| Maximum Likelihood & Error Functions
| Bishop, Ch.6
| |
Oct. 5
| The EM Algorithm for Density Estimation (Mixture Models)
| Bishop, Ch.2
Handout
| |
Oct. 10
|
The EM Algorithm for Supervised Learning (Mixture of Experts)
| Handout,
Homework 2
| |
Oct.12
|
The Theory of the EM Algorithm
| Handout will be sent by email
| |
Oct. 17
| Nonparametric Density Estimation and Classification
| Handout
| |
Oct. 19
|
Nonparametric Regression
| Handout
| |
Oct. 24
|
Data Preprocessing and Dimensionality Reduction
|
Bishop, Ch.8
| |
Oct. 26
| Bayesian Neural Networks
| Bishop, Ch.10
| |
Oct. 31
| Information Theory: Minimum Description Length, Entropy, and Mutual Information
| Bishop 6.10 & 10.10
| |
Nov. 2
| Hopefield Networks and Boltzmann Machines
| Handout
Homework 3
| |
Nov. 7
| Helmholtz Machines
| Handout1& Handout2
| |
Nov. 9
| Independent Component Analysis
| Handout
| |
Nov. 14
| Reinforcement Learning: Introduction and Dynamic Programming
| Electronic Book
| |
Nov. 16
| Reinforcement Learning: >Actor Critic Systems
| Electronic Book
| |
Nov.21
| TBA
|
Homework 4
| |
Nov.23
| TBA
|
| |
Nov. 28
| Review of class &
Project Presentations
|
Common Project
| |
Nov. 30
| Project Presentations
| Common Project
| |
Dec.9 (Friday)
| Short Final Exam (closed book)
:)
|
|
