Path: utzoo!attcan!uunet!lll-winken!ames!mailrus!wsu-cs!jal
From: jal@wsu-cs.uucp (Jason Leigh)
Newsgroups: comp.sys.amiga
Subject: Re: AI with Ami...Neural Nets
Keywords: neural, AI, gratuitous spam, Neural Nets
Message-ID: <566@wsu-cs.uucp>
Date: 1 Mar 89 13:34:26 GMT
References: <9472@louie.udel.EDU> <5244@hcr.UUCP>
Reply-To: jal@cs.wayne.edu (Jason Leigh)
Distribution: na
Organization: Computer Science Department, Wayne State University
Lines: 12


You do not necessarily have to have a machine capapble of forking
processes to build Neural Networks, although in some cases the result
may be gathered more quickly.  But you can write a neural network program
on a little Atari or a big Atari for that matter.
It depends on the kind of neural network you are trying to implement.
Using message ports in neural nets seems a considerable overhead if
not a waste since the only data that needs to be passed would be no
more than a few bytes.

I have build neural networks that solve travelling salesman problems
that can be written in BASIC on a pocket computer...