The ability of artificial neural networks to learn and generalize complex relationships from a collection of training examples has been established through numerous research studies in recent years. The knowledge acquired by neural networks, however, is considered incomprehensible and not transferable to other knowledge representation schemes such as expert or rule-based systems. Furthermore, the incomprehensibility of knowledge acquired by a neural network prevents users to gain better understanding of a classification task learned by the network. The aim of the present paper is to describe a method that can help to make the knowledge embedded in a trained neural network comprehensible, and thus transform neural networks into a powerful knowledge acquisition tool. Our method is based on rough sets, which offer a useful framework to reason about classification knowledge but lack in generalization capabilities. Unlike many existing methods that require training examples as well as the trained network to extract the knowledge embedded in numerical weights, our method works only with the weight matrix of trained network. No training examples are required. The suggested method has been applied to several trained neural networks with great success.
[1]
Aleksander Ohrn,et al.
ROSETTA -- A Rough Set Toolkit for Analysis of Data
,
1997
.
[2]
Andrzej Skowron,et al.
Chapter 19 the Design and Implementation of a Knowledge Discovery Toolkit Based on Rough Sets { the Rosetta System
,
1998
.
[3]
P. Lingras.
Rough Neural Networks
,
1996
.
[4]
Pawan Lingras,et al.
Comparison of Neofuzzy and Rough Neural Networks
,
1998,
Inf. Sci..
[5]
Janusz Zalewski,et al.
Rough sets: Theoretical aspects of reasoning about data
,
1996
.
[6]
Krzysztof Krawiec,et al.
Neural Networks and Rough Sets - Comparison and Combination for Classification of Histological Pictures
,
1993,
RSKD.
[7]
Lucila Ohno-Machado,et al.
Building manageable rough set classifiers
,
1998,
AMIA.
[8]
Ishwar K. Sethi,et al.
Symbolic mapping of neurons in feedforward networks
,
1996,
Pattern Recognit. Lett..