CMPU 395 Schedule
| M Aug 31 | Lecture 1 | Introduction, Presentation of the course | |
| W Sep 2 | Lecture 2 | Neurophysiology, Hodgkin-Huxley model | |
| W Sep 9 | Lecture 3 | Point neurons and compartment models, Synaptic interaction | |
| M Sep 14 | Lecture 4 | Integrate-and-fire models, Abstract models | Chapter 1 |
| W Sep 16 | Lecture 5 | Layered networks | Chapter 2 |
| F Sep 18 | Assignment 1 | H-H simulation | |
| M Sep 21 | Lecture 6 | Error driven learning | |
| W Sep 23 | Lecture 7 | Multi-Layered Perceptrons | Chapter 3 |
| M Sep 28 | Lecture 8 | Back-propagation learning | |
| W Sep 30 | Lecture 9 | Generalization, RBF networks | Chapter 4 |
| F Oct 2 | Assignment 2 | MLP classification | |
| M Oct 5 | Lecture 10 | Support Vector Machines, Structural Risk | Chapter 5 |
| W Oct 7 | Lecture 11 | Support Vector Machines, Kernels | |
| M Oct 12 | Lecture 12 | Concept learning, Decision trees | Chapter 6 |
| W Oct 14 | Lecture 13 | Boosting | Chapter 7 |
| F Oct 16 | Assignment 3 | SVM implementation | |
| – October break – | |||
| M Oct 26 | Lecture 14 | Competitive learning | Chapter 9 |
| W Oct 28 | Lecture 15 | Topology preserving maps | |
| M Nov 2 | Lecture 16 | Principal component analysis | Chapter 10 |
| W Nov 4 | Lecture 17 | Pattern association, Cell assemblies | |
| F Nov 6 | Assignment 4 | SOM implementation | |
| M Nov 9 | Lecture 18 | Hopfield networks | Chapter 11 |
| W Nov 11 | Lecture 19 | Boltzmann machines | Chapter 14 |
| M Nov 16 | Lecture 20 | Time sequences | |
| W Nov 18 | Lecture 21 | Markov models | Chapter 15 |
| F Nov 20 | Assignment 5 | Experiments with Hopfield network | |
| M Nov 23 | Lecture 22 | Reinforcement learning | Chapter 13 |
| W Nov 25 | Lecture 23 | State value estimation | |
| – Thanksgiving – | |||
| M Nov 30 | Lecture 24 | Temporal difference learning | |
| W Dec 2 | Lecture 25 | Genetic algorithms | Chapter 12 |
| F Dec 4 | Assignment 6 | Q-Learning | |
| M Dec 7 | Lecture 26 | Closure | |
