Record Details

A search technique for rule extraction from trained neural networks

DSpace at IIT Bombay

View Archive Info
 
 
Field Value
 
Title A search technique for rule extraction from trained neural networks
 
Creator KRISHNAN, R
SIVAKUMAR, G
BHATTACHARYA, P
 
Subject algorithms
feature extraction
knowledge acquisition
sorting
 
Description Search methods for rule extraction from neural networks work by finding those combinations of inputs that make the neuron active. By sorting the input weights to a neuron and ordering the weights suitably, it is possible to prune the search space. Based on this observation, we present an algorithm for rule extraction from feedforward neural networks with boolean inputs and analyze its properties.
 
Publisher Elsevier
 
Date 2009-05-08T02:30:44Z
2011-12-08T06:53:01Z
2011-12-26T13:01:50Z
2011-12-27T05:47:17Z
2009-05-08T02:30:44Z
2011-12-08T06:53:01Z
2011-12-26T13:01:50Z
2011-12-27T05:47:17Z
1999
 
Type Article
 
Identifier Pattern Recognition Letters 20(3), 273-280
0167-8655
10.1016/S0167-8655(98)00145-7
http://hdl.handle.net/10054/1288
http://dspace.library.iitb.ac.in/xmlui/handle/10054/1288
 
Language en