Fall 2006 schedule: Tuesday and Thursday 10:30-12 in 46-1015.
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, x2-1693 |
TAs: Jake Bouvrie, Viren Jain {jvb, viren}@mit.edu Office hours by appointment |
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.