9.641J / 8.594J Introduction to Neural Networks

Spring 2011 schedule:  Monday and Wednesday 2:30:4 in 46-5056.

Organization of synaptic connectivity as the basis of neural computation and learning. Perceptrons.  Dynamical theories of recurrent networks: amplifiers, attractors, and hybrid computation. Backpropagation and Hebbian learning.  Models of perception, motor control, memory, and neural development.

Prof. Sebastian Seung
seung@mit.edu
46-5065
TA: Mark Richardson
echo@mit.edu
Office hours by appointment

Lecture schedule

Homework assignments

Philosophy

Modern research in theoretical neuroscience can be divided into three categories:   cellular biophysics, network dynamics, and statistical analysis of neurobiological data.  This subject is about the dynamics of networks, but excludes the biophysics of single neurons, which will be taught in 9.29 Introduction to Computational Neuroscience.

This year, the course will emphasize a hands on approach to neural networks. A major focus of the class will be an independent research project on neural network models of early vision.

Prerequisites

Subject requirements

You can also access the 2002, 2005, and 2006 web page.