Using Genetic Programming to Extract Knowledge from Artificial Neural Networks

View Sample PDF

Author(s): Daniel Rivero (University of A Coruña, Spain), Miguel Varela (University of A Coruña, Spain)and Javier Pereira (University of A Coruña, Spain)
Copyright: 2008
Pages: 20
Source title: Artificial Intelligence for Advanced Problem Solving Techniques
Source Author(s)/Editor(s): Ioannis Vlahavas (Aristotle University, Greece)and Dimitris Vrakas (Aristotle University, Greece)
DOI: 10.4018/978-1-59904-705-8.ch013

Keywords: Artificial Intelligence / Computer Science & IT / Information Science Reference

Purchase

View Using Genetic Programming to Extract Knowledge from Artificial Neural Networks on the publisher's website for pricing and purchasing information.

Abstract

A technique is described in this chapter that makes it possible to extract the knowledge held by previously trained artificial neural networks. This makes it possible for them to be used in a number of areas (such as medicine) where it is necessary to know how they work, as well as having a network that functions. This chapter explains how to carry out this process to extract knowledge, defined as rules. Special emphasis is placed on extracting knowledge from recurrent neural networks, in particular when applied in predicting time series.

The IRMA Community

Research IRM

Using Genetic Programming to Extract Knowledge from Artificial Neural Networks

Purchase

Abstract

Related Content

IRMA Sponsors