Path: utzoo!attcan!uunet!ginosko!usc!neuro.usc.edu!death
From: death@neuro.usc.edu
Newsgroups: comp.ai.neural-nets
Subject: Re: Good book on Neural Nets.
Keywords: neural nets introduction book
Message-ID: <19576@usc.edu>
Date: 30 Aug 89 08:47:21 GMT
References: <294@uvacs.cs.Virginia.EDU> <5922@tekigm2.MEN.TEK.COM>
Sender: news@usc.edu
Reply-To: death%neuro.usc.edu@usc.edu (the grim reaper of zombie processes)
Organization: University of Southern California, Los Angeles, CA
Lines: 63

>> I am looking for a good introductory text on Neural Nets. 

NO ONE BOOK CAN DO THE JOB -- YOU NEED TO READ AND READ AND READ BOOKS,
JOURNAL ARTICLES, REVIEW ARTICLES, CONFERENCE PROCEEDINGS, ETC.  BUT A
GOOD STARTING POINT (FOR THE SERIOUS RESEARCHER) FOLLOWS:

Koch, Christof and Idan Segev.  Methods in Neuronal Modeling: From Synapses
to Networks.  MIT Press:Cambridge 1989.  This is an excellent collection of
papers from the Woods Hole Neural Network Modeling Course in August, 1988.
The first five chapters develop a set of mathematical modeling tools that
would help anyone with a minimal background in calculus, linear algebra and 
differential equations to begin a serious modeling project.

Rumelhardt, McClelland & PDP Research Group.  Parallel Distributed Processing
(and workbook: Explorations in PDP with floppy disks containing source code
in C for the IBM PC) MIT Press:1986.  Everyone has read it.  It you haven't
you need to read it to be able to talk to everyone else.

MacGregor, Ronald J.  Neural and Brain Modeling.  Academic Press:1987.  This
book has lotsa FORTRAN listings for hackers and such.  But, serious research
people should use it as an initial summary of past neural network experiments
designed to simulate specific subsystems of the brain.  Read the summaries --
THEN READ THE PAPERS REFERENCED IN THE FOOTNOTES of your favorite section.
There are errors in some of the programs ... so recheck the code carefully
... and understand the purpose of every parameter, variable and statement.

Kandel, Eric R and James H. Schwartz.  Principles of Neural Science.  2nd ed.
Elsevier:New York 1985.  A solid overview of how the nervous system works.

Hille, Bertil.  Ionic Channels of Excitable Membranes.  Sinauer Associates,
Inc: Sunderland 1984.  Everything you ever wanted to know about how nerves
and synapses work.  Essential for building blocks for real neural networks.
Researchers should design abstract neurons for their systems based on the
behaviour of detailed compartmental models of such realistic neurons.

Carpenter, Malcolm B.  Human Neuroanatomy.  The Williams and Wilkins Company:
Baltimore.  7ed:1976.  Overview of the gross structural divisions of the 
nervous system.  Pay particular attention to the chapters on the central
nervous system (medulla, pons, mesencephalon, cerebellum, diencephalon,
hypothalamus, basal ganglia, olfaction, hippocampus, amygdala, cerebral ctx).
This book is one of the better arguments for building hierarchical neural
network models in order to capture biological neural network behaviours.

Brodal, A.  Neurological Anatomy.  3rd ed.  Oxford Univ Press:New York 1981.
Contains many detailed chapters about pathways and information transmission
among major regions of the brain.  Read this one to learn a little about the
vast amount already known about information transmission pathways and the
actual functions performed by those pathways in real brains.

Purves, Dale and Jeff W. Lichtman.  Principles of Neural Development.  
Sinauer Associates Inc:1985.  You could learn a lot about how to build an
artificial neural network by studying how natural neural networks develop.

McGeer, Patrick L, Sir John Eccles, and Edith McGeer.  Molecular Neurobiology
of the Mamalian Brain.  2nd ed.  Plenum Press:1987.  There are a lot more
signaling systems in the brain than electrical or chemical synapses.  Study
this book to learn about long term wide area signaling systems modulating
natural brain function.

Matkowitsch, Hans J.  Information Processing in the Brain.  Hans Huber 
Publishers:Toronto:1988.  A good introduction to developing the ability
to critically read and understand papers from real neurophysiology journals
like: Experimental Brain Research, Journal of Neuroscience & Neurosurgery.