In this paper we propose a new algorithm for rule extraction from a trained Multilayer Feedforward network. The algorithm is based on an interval arithmetic network inversion for p...
A method to extract a fuzzy rule based system from a trained artificial neural network for classification is presented. The fuzzy system obtained is equivalent to the correspondin...
Although backpropagation ANNs generally predict better than decision trees do for pattern classification problems, they are often regarded as black boxes, i.e., their predictions c...
This paper presents our approach to the rule extraction problem from trained neural network. A method called REX is briefly described. REX acquires a set of fuzzy rules using an ev...