Machine Learning
NeuroLinear: A System for Extracting Oblique Decision Rules from Neural Networks
ECML '97 Proceedings of the 9th European Conference on Machine Learning
Extracting Provably Correct Rules from Artificial Neural Networks
Extracting Provably Correct Rules from Artificial Neural Networks
Neural Networks: A Comprehensive Foundation (3rd Edition)
Neural Networks: A Comprehensive Foundation (3rd Edition)
An empirical measure of element contribution in neural networks
IEEE Transactions on Systems, Man, and Cybernetics, Part C: Applications and Reviews
IEEE Transactions on Neural Networks
Query-based learning applied to partially trained multilayer perceptrons
IEEE Transactions on Neural Networks
Query-based learning for aerospace applications
IEEE Transactions on Neural Networks
Rule extraction from trained adaptive neural networks using artificial immune systems
Expert Systems with Applications: An International Journal
Extracting rules for classification problems: AIS based approach
Expert Systems with Applications: An International Journal
TACO-miner: An ant colony based algorithm for rule extraction from trained neural networks
Expert Systems with Applications: An International Journal
Engineering Applications of Artificial Intelligence
Reverse Engineering the Neural Networks for Rule Extraction in Classification Problems
Neural Processing Letters
A hybrid intelligent system for medical data classification
Expert Systems with Applications: An International Journal
Hi-index | 0.01 |
An important drawback of many artificial neural networks (ANN) is their lack of explanation capability [Andrews, R., Diederich, J., & Tickle, A. B. (1996). A survey and critique of techniques for extracting rules from trained artificial neural networks. Knowledge-Based Systems, 8, 373-389]. This paper starts with a survey of algorithms which attempt to explain the ANN output. We then present HYPINV, a new explanation algorithm which relies on network inversion; i.e. calculating the ANN input which produces a desired output. HYPINV is a pedagogical algorithm, that extracts rules, in the form of hyperplanes. It is able to generate rules with arbitrarily desired fidelity, maintaining a fidelity-complexity tradeoff. To our knowledge, HYPINV is the only pedagogical rule extraction method, which extracts hyperplane rules from continuous or binary attribute neural networks. Different network inversion techniques, involving gradient descent as well as an evolutionary algorithm, are presented. An information theoretic treatment of rule extraction is presented. HYPINV is applied to example synthetic problems, to a real aerospace problem, and compared with similar algorithms using benchmark problems.