Syllabus:

Course information

Lecture schedule

Readings and lecture notes

Intro lecture slides

Matlab intro

Linear algebra

Linear neuron

Receptive field models

Linear, time-invariant systems

Dynamics

Simulating differential equations

Fourier analysis

Supervised learning I

Supervised learning II

Linear Hebbian learning and PCA

Attractor neural networks

A probability primer

Bayesian inference

The mixture of Gaussians model

Information theory

Labs:

Lab #1 - Matlab

• astronaut.mat

Lab #2 - Model fitting and linear systems

• hw1.mat
• DOG.mat
• Gaborh.mat
• Gaborv.mat
• edges.mat
• einstein.mat

Lab #3 - Cell membrane model

Lab #4 - Frequency analysis

• Chordgliss.mat
• voc2.wav
• sentence1.wav
• sentence2.wav
• specgram.m
• win.m

Lab #5 - Sound synthesis

• immigrant2.wav

Lab #6 - Supervised learning

• apples.mat
• oranges.mat
• lab61.m
• lab61c.m
• apples2.mat
• oranges2.mat
• lab62.m
• sigmoid.m
  

Lab #7 - Unsupervised learning

• data2d.mat
• hebb.m
• faces2.mat

Lab #8 - Competitive learning, Kohonen nets, Hopfield nets

• comphebb.m
• kohonen.m
• showrfs.m
• hopnet-instructions
• hopnet.m
• patterns.mat
• genpat.m

• mog.m
• X.mat