Computer Science and Engineering 90
				Neural Networks

		    Professor: Gary Cottrell APM Prime 4872
				Phone: 534-6640
				 Email:	gary@cs

	    Office Hours: Mondays 1:30-2:30PM, Thursdays 3-3PM or by
				  appointment.

				     NOTE:
	  CLASS	MEETS FOUR TIMES WEEKS ONLY!!: 4/04, 4/11, 4/18/ and 4/251

	  Course Description

	  This is a one	credit course that will	meet for 4 weeks,  two
	  hours	 per  session.	This course will explore connectionist
	  (or Parallel Distributed Processing,	or  artificial	Neural
	  network)  models  and	their relation to cognitive processes.
	  We will cover	 what  neural  networks	 are,  their  use  and
	  current learning methods for them.  We will also look	at the
	  application of the models to several problems	 in  cognitive
	  modeling.  Use of demonstration programs will	be an integral
	  part of this course. Each week I will	try to limit myself to
	  talking  for	one  hour,  and	 then  we  will	 "play"	on the
	  computer for an hour.

	  Week 1  will	motivate  why  we  are	interested  in	neural
	  networks  as	models	of  cognition.	We will	also try out a
	  simple model or two on the computer.	Week 2 will cover more
	  models,  especially  so-called "attractor networks" as model
	  of  memory,  using  the  Jets	 &  the	 Sharks	 example  (iac
	  program).   Week 3 will introduce learning using perceptrons
	  and back propagation.	 Week  4  will	look  at  learning  in
	  recurrent  networks  (Elman and Jordan networks and others).
	  This week we will also go over to my lab in AP&M  prime  and
	  see a	couple of demonstrations.

	  Required Work

	  The only required work  consists  of	attending  class  each
	  week.	 I will	actually take attendance. If you miss a	class,
	  you will receive an NP (or a U or whatever it	is).  The only
	  way  to  make	this up	is to write a five page	paper covering
	  some aspect of neural	networks of interest to	you.  This may
	  be a "thought	piece",	suggesting how neural nets may explain
	  some aspect of human cognition, or a simple regurgitation of
	  some	of the things you learned in the course, or a write-up
	  of  a	 (very	small!)	  project  using  the  PDP  simulation
	  software (see	the "Explorations" book	below).
















	  Slides

	  Many of the slides I present are available at	soft  reserves
	  for a	small fee.

	  Recommended Text

	  Explorations in Parallel Distributed Processing,  McClelland
	  &  Rumelhart,	 MIT  Press, 1988. ($52.95 on Amazon.com) This
	  spiral-bound volume comes with two floppies for  a  PC  with
	  several  programs  for simulating neural networks.  There is
	  also a Mac version.

	  Also recommended is Parallel Distributed Processing, Vols  1
	  and  2,  edited by Rumelhart and McClelland. MIT Press, 1986
	  ($27.50 for one volume on amazon.com)	These books  are  ones
	  you  will  want  to  have  if	 you  plan on eventually doing
	  research in Cognitive	Science.

	  Check	for these books	both under the class in	the  bookstore
	  and  in  the	general	book section. Let me know if you can't
	  find them.