Path: utzoo!utgpu!jarvis.csri.toronto.edu!clyde.concordia.ca!uunet!mailrus!tut.cis.ohio-state.edu!unmvax!ariel!wayback.unm.edu!bill
From: bill@wayback.unm.edu (william horne)
Newsgroups: comp.ai.neural-nets
Subject: Re: Computational Learning (intro needed)
Keywords: Reference for Book
Message-ID: <1546@ariel.unm.edu>
Date: 8 Feb 90 19:45:09 GMT
References: <689@h.cs.wvu.wvnet.edu> <2937@bingvaxu.cc.binghamton.edu> <1990Feb8.033651.18574@Neon.Stanford.EDU>
Sender: news@ariel.unm.edu
Reply-To: bill@wayback.unm.edu (william horne)
Organization: University of New Mexico, Albuquerque
Lines: 12

What come to be know as Computational Learning Theory is actually an
offshoot of work by Valient.  In fact, the Computational Learning Theory
(COLT) Conferences, are centered around Valient's approach to learning.
An introductory reference is:

Valient, L.G., "A Theory of the Learnable", Comm. of the ACM, v27, n11
	pp. 1134-1142.

Nils Nilsson's book, Learning Machines, is kind of a precursor to
conventional pattern recognition, for which a better book is clearly

Duda & Hart, Pattern Classification and Scene Analysis