Knowledge Extraction from Neural Networks using the All-Permutations Fuzzy Rule Base
Eyal Kolman, Michael Margaliot · 2005
A major drawback of artificial neural networks is their black-box character. Even when the trained network performs adequately, it is very di#cult to understand its operation. In this paper, we use the mathematical equivalence between artificial neural networks and a specific fuzzy rule base to extract the knowledge embedded in the network. We demonstrate this using a benchmark problem: the recognition of digits produced by a LED device. The method provides a symbolic and comprehensible description of the knowledge learned by the network during its training.