A novel method for extracting knowledge from neural networks with evolving SQL queries

Authors:
Mario A. Góngora;Tim Watson;David A. Elizondo
Affiliations:
School of Computing, Faculty of Computing Sciences and Engineering, De Montfort University, Leicester, UK;School of Computing, Faculty of Computing Sciences and Engineering, De Montfort University, Leicester, UK;School of Computing, Faculty of Computing Sciences and Engineering, De Montfort University, Leicester, UK
Venue:
ICANN'05 Proceedings of the 15th international conference on Artificial neural networks: formal models and their applications - Volume Part II
Year:
2005

Citing 4
Cited 0

Evolving SQL Queries for Data Mining

IDEAL '02 Proceedings of the Third International Conference on Intelligent Data Engineering and Automated Learning
Extract Rules from Software Quality Prediction Model Based on Neural Network

ICTAI '04 Proceedings of the 16th IEEE International Conference on Tools with Artificial Intelligence
Rule extraction from an RBF classifier based on class-dependent features

CEC '02 Proceedings of the Evolutionary Computation on 2002. CEC '02. Proceedings of the 2002 Congress - Volume 02
A new methodology of extraction, optimization and application of crisp and fuzzy logical rules

IEEE Transactions on Neural Networks

Quantified Score

Hi-index	0.00

Visualization

Abstract

While artificial neural networks (ANNs) are undoubtedly powerful classifiers their results are sometimes treated with suspicion. This is because their decisions are not open to inspection - the knowledge they contain is hidden. In this paper we describe a method for extracting and representing the knowledge within an ANN. Mappings between inputs and output classifications are stored in a table and, for each classification, Structured Query Language (SQL) queries are evolved using a genetic algorithm. Each evolved query is a simple, humanreadable representation of the knowledge used by the ANN to decide on the classification based on the inputs. This method can also be used to show how the knowledge within an ANN develops as it is trained, and can help to identify problems that are particularly hard, or easy, for ANNs to classify.