Automatic Recurrent and Feed-Forward ANN Rule and Expression Extraction with Genetic Programming

Authors:
Julian Dorado;Juan R. Rabuñal;Antonino Santos;Alejandro Pazos;Daniel Rivero
Affiliations:
-;-;-;-;-
Venue:
PPSN VII Proceedings of the 7th International Conference on Parallel Problem Solving from Nature
Year:
2002

Citing 15
Cited 1

Using the genetic algorithm to generate LISP source code to solve the prisoner's dilemma

Proceedings of the Second International Conference on Genetic Algorithms on Genetic algorithms and their application
Genetic programming: on the programming of computers by means of natural selection

Genetic programming: on the programming of computers by means of natural selection
On the equivalence of neural nets and fuzzy expert systems

Fuzzy Sets and Systems
Genetic programming II: automatic discovery of reusable programs

Genetic programming II: automatic discovery of reusable programs
Knowledge-based artificial neural networks

Artificial Intelligence
Advances in knowledge discovery and data mining

Advances in knowledge discovery and data mining
Genetic Programming III: Darwinian Invention & Problem Solving

Genetic Programming III: Darwinian Invention & Problem Solving
Data Mining Using Grammar-Based Genetic Programming and Applications

Data Mining Using Grammar-Based Genetic Programming and Applications
A Representation for the Adaptive Generation of Simple Sequential Programs

Proceedings of the 1st International Conference on Genetic Algorithms
Statistical Control of RBF-like Networks for Classification

ICANN '97 Proceedings of the 7th International Conference on Artificial Neural Networks
Strongly typed genetic programming

Evolutionary Computation
A learning machine: part II

IBM Journal of Research and Development
A learning machine: part I

IBM Journal of Research and Development
Are artificial neural networks black boxes?

IEEE Transactions on Neural Networks
The truth will come to light: directions and challenges in extracting the knowledge embedded within trained artificial neural networks

IEEE Transactions on Neural Networks

Time series forecast with anticipation using genetic programming

IWANN'05 Proceedings of the 8th international conference on Artificial Neural Networks: computational Intelligence and Bioinspired Systems

Quantified Score

Hi-index	0.00

Visualization

Abstract

Various rule-extraction techniques using ANN have been used so far, most of them being applied on multi-layer ANN, since they are more easily handled. In many cases, extraction methods focusing on different types of networks and training have been implemented. However, there are virtually no methods that view the extraction of rules from ANN as systems which are independent from their architecture, training and internal distribution of weights, connections and activation functions. This paper proposes a rule-extraction system of ANN regardless of their architecture (multi-layer or recurrent), using Genetic Programming as a rule-exploration technique.