An IJCAI-01 paper and its demo

[zhouzh]

Dear colleagues,

Below is a paper to be presented at IJCAI-01:

Title: Genetic algorithm based selective neural network ensemble
Author: Zhi-Hua Zhou, Jian-Xin Wu, Yuan Jiang, and Shi-Fu Chen

Abstract: Neural network ensemble is a learning paradigm where several
neural networks are jointly used to solve a problem. In this paper,
the relationship between the generalization ability of the neural
network ensemble and the correlation of the individual neural networks
is analyzed, which reveals that ensembling a selective subset of
individual networks is superior to ensembling all the individual
networks in some cases. Therefore an approach named GASEN is proposed,
which trains several individual neural networks and then employs
genetic algorithm to select an optimum subset of individual networks
to constitute an ensemble. Experimental results show that, comparing
with a popular ensemble approach, i.e. averaging all, and a
theoretically optimum selective ensemble approach, i.e. enumerating,
GASEN has preferable performance in generating ensembles with strong
generalization ability in relatively small computational cost.

The paper is available at
http://cs.nju.edu.cn/people/zhouzh/zhouzh.files/Publication/zwjc_ijcai01.pdf

Its demo is available at
http://cs.nju.edu.cn/people/zhouzh/zhouzh.files/MLNN_Group/freeware/Gasen.zip

Regards
Zhihua
-----------------------------------------------
Zhi-Hua ZHOU        Ph.d.

National Lab for Novel Software Technology
Nanjing University
Hankou Road 22
Nanjing 210093, P.R.China
 
Tel: +86-25-359-3163      Fax: +86-25-330-0710
URL: http://cs.nju.edu.cn/people/zhouzh/
Email: zhouzh at nju.edu.cn
-----------------------------------------------