Pedagogical Method for Extraction of Symbolic Knowledge from Neural Networks

Authors:
Krzysztof Krawiec;Roman Slowinski;Irmina Szczesniak
Affiliations:
-;-;-
Venue:
RSCTC '98 Proceedings of the First International Conference on Rough Sets and Current Trends in Computing
Year:
1998

Citing 9
Cited 1

Connectionist expert systems

Communications of the ACM
A neural expert system with automated extraction of fuzzy if-then rules and its application to medical diagnosis

NIPS-3 Proceedings of the 1990 conference on Advances in neural information processing systems 3
Explanation and artificial neural networks

International Journal of Man-Machine Studies
C4.5: programs for machine learning

C4.5: programs for machine learning
Knowledge-based artificial neural networks

Artificial Intelligence
The Foundations of Artificial Intelligence: A SourceBook

The Foundations of Artificial Intelligence: A SourceBook
Induction of Decision Trees

Machine Learning
Extracting Provably Correct Rules from Artificial Neural Networks

Extracting Provably Correct Rules from Artificial Neural Networks
Extracting comprehensible models from trained neural networks

Extracting comprehensible models from trained neural networks

An investigation of TREPAN utilising a continuous oracle model

International Journal of Data Analysis Techniques and Strategies

Quantified Score

Hi-index	0.00

Visualization

Abstract

This paper addresses the extraction of symbolic knowledge from trained artificial neural networks. Specifically, for that purpose the so-called pedagogical approach is incorporated, where the trained network is used as an oracle when inducing the symbolic description. We present an essential extension of the TREPAN algorithm proposed originally by Craven and Shavlik [4][5]. The crucial modification concerns the way of generating artificial training instances. The paper ends with an empirical verification of the proposed method on popular machine learning benchmarks and comparison with the original TREPAN.