From mboxrd@z Thu Jan 1 00:00:00 1970 X-Msuck: nntp://news.gmane.io/gmane.science.mathematics.categories/4888 Path: news.gmane.org!not-for-mail From: mjhealy@ece.unm.edu Newsgroups: gmane.science.mathematics.categories Subject: Applying Category Theory to Improve ... Date: Tue, 26 May 2009 15:56:37 -0600 (MDT) Message-ID: Reply-To: mjhealy@ece.unm.edu NNTP-Posting-Host: lo.gmane.org Content-Type: text/plain;charset=iso-8859-1 Content-Transfer-Encoding: quoted-printable X-Trace: ger.gmane.org 1243389125 22827 80.91.229.12 (27 May 2009 01:52:05 GMT) X-Complaints-To: usenet@ger.gmane.org NNTP-Posting-Date: Wed, 27 May 2009 01:52:05 +0000 (UTC) To: categories@mta.ca Original-X-From: categories@mta.ca Wed May 27 03:52:03 2009 Return-path: Envelope-to: gsmc-categories@m.gmane.org Original-Received: from mailserv.mta.ca ([138.73.1.1]) by lo.gmane.org with esmtp (Exim 4.50) id 1M98JF-0003CV-Ro for gsmc-categories@m.gmane.org; Wed, 27 May 2009 03:52:02 +0200 Original-Received: from Majordom by mailserv.mta.ca with local (Exim 4.61) (envelope-from ) id 1M97nc-00049y-OT for categories-list@mta.ca; Tue, 26 May 2009 22:19:20 -0300 Original-Sender: categories@mta.ca Precedence: bulk Xref: news.gmane.org gmane.science.mathematics.categories:4888 Archived-At: Our full account of an application of colimits and limits to improving upon a standard neural architecture is soon to appear in the journal Neurocomputing. In case this interests you, a preprint is obtainable fro= m my website, http://www.ece.unm.edu/~mjhealy , or else contact me for a copy. The blurb: Applying Category Theory to Improve the Performance of a Neural Architect= ure Michael J. Healy, Richard D. Olinger, Robert J. Young, Shawn E. Taylor, Thomas P. Caudell, and Kurt W. Larson Abstract: A recently-developed mathematical semantic theory explains the relationship between knowledge and its representation in connectionist systems. The semantic theory is based upon category theory, the mathematical theory of structure. A product of its explanatory capability is a set of principles to guide the design of future neural architectures and enhancements to existing designs. We claim that this mathematical semantic approach to network design is an effective basis for advancing the state of the art. We offer two experiments to support this claim. One of these involves multispectral imaging using data from a satellite camera. [For admin and other information see: http://www.mta.ca/~cat-dist/ ]