Presentation 1998/6/18
Rule Extraction from Neural Networks Formed Using Evolutionary Algorithms
Minoru FUKUMI, Norio AKAMATSU,
PDF Download Page PDF download Page Link
Abstract(in Japanese) (See Japanese page)
Abstract(in English) This paper presents a method of extracting rules from neural networks trained using a random optimization method (ROM) with deterministic mutation (DM). The DM is performed on the basis of the result of neural network structure learning. The ROM with the DM is utilized to reduce the number of network connections for iris data. The network connections survived after training represent rules to perform pattern classification for the iris data. The rules are then extracted from the neural network in which hidden units use signum output functions to produce binary values. It enables us to extract simple logical functions from the network. Simulation results for the iris data show this method can generate simple rules compared with conventional methods.
Keyword(in Japanese) (See Japanese page)
Keyword(in English) evolutionary algorithm / rule extraction / deterministic mutation / structure learning
Paper # NC98-22,HIP98-13
Date of Issue

Conference Information
Committee HIP
Conference Date 1998/6/18(1days)
Place (in Japanese) (See Japanese page)
Place (in English)
Topics (in Japanese) (See Japanese page)
Topics (in English)
Chair
Vice Chair
Secretary
Assistant

Paper Information
Registration To Human Information Processing (HIP)
Language JPN
Title (in Japanese) (See Japanese page)
Sub Title (in Japanese) (See Japanese page)
Title (in English) Rule Extraction from Neural Networks Formed Using Evolutionary Algorithms
Sub Title (in English)
Keyword(1) evolutionary algorithm
Keyword(2) rule extraction
Keyword(3) deterministic mutation
Keyword(4) structure learning
1st Author's Name Minoru FUKUMI
1st Author's Affiliation University of TOKUSHIMA()
2nd Author's Name Norio AKAMATSU
2nd Author's Affiliation University of TOKUSHIMA
Date 1998/6/18
Paper # NC98-22,HIP98-13
Volume (vol) vol.98
Number (no) 130
Page pp.pp.-
#Pages 8
Date of Issue