Paper available: Task Decomposition and Modular Neural Net

[Bao-Liang Lu]

The following paper, appeared in Lecture Notes in Computer Science, 
vol. 1240, 1997, Springer, is available via anonymous FTP.

(This work was presented at International Work-Conference on 
Artificial and Natural Neural Networks (IWANN'97), 4-6 June 1997,
Lanzarote, Canary Islands, Spain )

FTP-host:ftp.bmc.riken.go.jp

FTP-file:pub/publish/Lu/lu-iwann97.ps.gz

==========================================================================
TITLE: Task Decomposition Based on Class Relations: A Modular Neural
       Network Architecture for Pattern Classification

AUTHORS:
       Bao-Liang Lu 
       Masami Ito 

ORGANISATIONS:
       Bio-Mimetic Control Research Center,
       The Institute of Physical and Chemical Research (RIKEN)
 
ABSTRACT:
In this paper, we propose a new methodology for decomposing 
pattern classification problems based on the class relations among 
training data. We also propose two combination principles for 
integrating individual modules to solve the original problem. 
By using the decomposition methodology, we can divide a $K$-class 
classification problem into ${K\choose 2}$ relatively smaller 
two-class classification problems. If the two-class problems are 
still hard to be learned, we can further break down them into a set of 
smaller and simpler two-class problems. Each of the two-class problem 
can be learned by a modular network independently. After learning, 
we can easily integrate all of the modules according to the combination 
principles to get the solution of the original problem. Consequently, 
a $K$-class classification problem can be solved effortlessly 
by learning a set of smaller and simpler two-class classification 
problems in parallel


(10 pages )

Bao-Liang Lu
======================================
Bio-Mimetic Control Research Center
The Institute of Physical and Chemical Research (RIKEN)
Anagahora, Shimoshidami, Moriyama-ku
Nagoya 463, Japan
Tel: +81-52-736-5870
Fax: +81-52-736-5871
Email: lbl at bmc.riken.go.jp