g Neural Networks into netic Algorithms and ierarchical Aproach
Vasile Palade, Severin Bumbaru, G. Negoita · 1998
Neural networks have been criticized for their lack of human comprehensibility, which make them to appear as black box structures to the user. This paper proposes a mechanism that compile a neural network into an equivalent set of fuzzy rules. Genetic algorithms are used to find the right structure of the fuzzy model equivalent with the neural network, and then to find the best shape of the membership functions. In order to reduce the number of fuzzy rules, we look for a hierarchical structure of the fuzzy system, considering the relations between the network inputs.