CSE 590NC: Neural
Computation
Welcome to CSE
590NC! This is a new seminar on Neural Computation, being offered for
the first time in Autumn, 2001. The plan is to discuss one or more
papers per week, diverging as necessary into detail on topics that are
of particular interest to seminar attendees.
We meet on Tuesdays from 1:30 to 2:30pm in
Loew 111.
What is the seminar all about? Our primary
focus is on neurally-inspired algorithms for learning and sensorimotor
control. While some papers will address computational models of
neurobiological systems, others will involve implementations of
neurally-inspired algorithms in software (e.g. in computer vision and
robotics) and in hardware (e.g. in analog VLSI).
There is a list of presentations with links to appropriate
papers and background reading.
A preliminary list of the broad subject areas that we could pick papers from:
- Supervised versus unsupervised learning
- Reinforcement versus imitation learning
- Bayesian versus Neural Networks
- Recurrent and Hierarchical Networks
- Applications in Vision, Robotics, and Brain-Computer Interfaces
Papers from other related subject areas may also be picked if there is sufficient interest in the class.
Mailing List: Be sure to join
the class mailing list and browse the email
archive. To join, send a message to majordomo@cs.washington.edu,
and include the following in the body of your message: subscribe
cse590nc
You should get a response quickly that you have been
added.
Online resources: Click here to check out an introductory online neurobiology tutorial.
Credit Hours: 1
Grading: Credit/No Credit (enrolled students are expected to present one or more papers and participate in class discussions)