Relay-Version: version B 2.10 5/3/83; site utzoo.UUCP
Path: utzoo!mnetor!uunet!seismo!sundc!pitstop!sun!decwrl!ucbvax!giraffe..arpa!krulwich
From: krulwich@giraffe..arpa (Bruce Krulwich)
Newsgroups: comp.ai.digest
Subject: Re: Boltzmann Machine
Message-ID: <16949@yale-celray.yale.UUCP>
Date: Wed, 30-Sep-87 17:21:50 EDT
Article-I.D.: yale-cel.16949
Posted: Wed Sep 30 17:21:50 1987
Date-Received: Tue, 6-Oct-87 04:01:45 EDT
References: <8709271925.AA14103@uvaee.ee.Virginia.EDU>
Sender: daemon@ucbvax.BERKELEY.EDU
Reply-To: yale.ARPA!krulwich@uunet.uu.net (Bruce Krulwich)
Organization: Yale University Computer Science Dept, New Haven CT
Lines: 26
Keywords: Boltzmann machine, connectionism
Approved: ailist@kl.sri.com
Summary: Machines need input



> Since the expression for dG/dWij is the same in both cases, the
> definitions of Pij- must be equivalent. The only explanation I could
> think of was that "clamping" the inputs ONLY was the same thing as letting
> the environment have a free run of them, so the case being described is
> the free-running one.


The point is that for any given inputs learning is done by comparing
the desired outputs with the outputs computed by the machine.  This
called monitored learning, and is similar in this sense to back
propogation learning.  This is used for networks that perform a
computation based on some input being clamped in the input units.
When the output units are clamped, the P values are something like
what they "should" be, so comparing these to the P values for
unclamped output units lets you approximate the error between the
units in qestion and learn from it.


Bruce Krulwich

ARPA:   krulwich@yale.arpa		      If you're right 95% of the time,
     or krulwich@cs.yale.edu		      why worry about the other 3% ??
Bitnet:	krulwich@yalecs.bitnet
UUCP:   {harvard, seismo, ihnp4}!yale!krulwich