Affiliation:
1. University of Regina, Canada
Abstract
This paper discusses development and application of a decomposition neural network rule extraction algorithm for nonlinear regression problems. The algorithm is called the piece-wise linear artificial neural network or PWL-ANN algorithm. The objective of the algorithm is to “open up” the black box of a neural network model so that rules in the form of linear equations are generated by approximating the sigmoid activation functions of the hidden neurons in an artificial neural network (ANN). The preliminary results showed that the algorithm gives high fidelity and satisfactory results on sixteen of the nineteen tested datasets. By analyzing the values of R2 given by the PWL approximation on the hidden neurons and the overall output, it is evident that in addition to accurate approximation of each individual node of a given ANN model, there are more factors affecting the fidelity of the PWL-ANN algorithm Nevertheless, the algorithm shows promising potential for domains when better understanding about the problem is needed.
Reference24 articles.
1. Eclectic extraction of propositional rules from Neural Networks
2. Survey and critique of techniques for extracting rules from trained artificial neural networks
3. Rule Extraction from Neural networks - a Comparative Study. Proceedings of the;M. G.Augasta;International Conference on Pattern Recognition, Informatics and Medical Engineering,2012
4. Development of an Ontology for an Industrial Domain
5. Extracting tree-structured representations of trained neural networks.;M. W.Craven;Advances in Neural Information Processing Systems,1996