Newsgroups: comp.ai.neural-nets
Path: cantaloupe.srv.cs.cmu.edu!das-news2.harvard.edu!news2.near.net!howland.reston.ans.net!vixen.cso.uiuc.edu!uwm.edu!uwvax!newssinet!news.u-tokyo.ac.jp!news.tisn.ad.jp!riksun!nagoya!lbl
From: lbl@nagoya.riken.go.jp (Bao-Liang Lu)
Subject: Re: Constructing Neural Nets - does a methodology exist???
Message-ID: <1995Apr10.013545.10668@riksun.riken.go.jp>
Sender: news@riksun.riken.go.jp
Nntp-Posting-Host: ankara
Reply-To: lbl@nagoya.riken.go.jp
Organization: Sun Microsystems
References: <Js-fA8r.predictor@delphi.com>
Date: Mon, 10 Apr 1995 01:35:45 GMT
Lines: 36


In article Craig Munday <cmunday@neumann.une.edu.au> writes:
> 
>I am looking for papers that describe any type of heuristic method
>of constructing Artificial Neural Networks for classification type problems.
>
>If you happen to be working in this area or know of papers that maybe
>be relevant, then I would like to hear about them.


We have proposed a constructing neural network architecture for 
pattern classification. We'll present this work at
"Fourth International Conference on  Artificial Neural Networks", 
Cambridge, UK, June 26-28, 1995. 

Title: A Parallel and Modular Multi-sieving Neural Network Architecture
       for Constructive Learning

Abstract: In this paper we present a parallel and modular multi-sieving 
neural network (PMSN) architecture for constructive learning. This PMSN
architecture is different from existing constructive learning networks 
such as the cascade correlation architecture. The constructing element 
of the PMSNs is a compound modular network rather than a hidden unit. This 
compound modular network is called a sieving module (SM). In the PMSN a 
complex learning task is docomposed into a set of relatively simple
subtasks automatically. Each of these subtasks is solved by a 
corresponding individual SM and all of these SMs are processed in parallel.
 
Bao-Liang Lu
---------------------------------------------
Bio-Mimetic Control Research Center, RIKEN
3-8-31 Rokuban, Atsuta-ku, Nagoya 456, Japan
Phone: +81-52-654-9137
Fax: +81-52-654-9138
Email: lbl@nagoya.riken.go.jp

