9.641J | Spring 2005 | Graduate

Introduction to Neural Networks

Lecture Notes

Lec # Topics
1 From Spikes to Rates (PDF)
2 Perceptrons: Simple and Multilayer
3 Perceptrons as Models of Vision
4 Linear Networks
5 Retina
6 Lateral Inhibition and Feature Selectivity (PDF 1) (PDF 2) (PDF 3)
7 Objectives and Optimization
8 Hybrid Analog-Digital Computation

Ring Network

9 Constraint Satisfaction

Stereopsis

10 Bidirectional Perception
11 Signal Reconstruction
12 Hamiltonian Dynamics (PDF)
13 Antisymmetric Networks (PDF)
14 Excitatory-Inhibitory Networks (PDF)

Learning

15 Associative Memory
16 Models of Delay Activity

Integrators

17 Multistability

Clustering

18 VQ (PDF)

PCA (PDF)

19 More PCA

Delta Rule (PDF)

20 Conditioning (PDF)

Backpropagation (PDF)

21 More Backpropagation (PDF)
22 Stochastic Gradient Descent
23 Reinforcement Learning
24 More Reinforcement Learning
25 Final Review

Course Info

As Taught In
Spring 2005
Level
Learning Resource Types
Lecture Notes
Problem Sets