Estimating module relevance with Sugeno integration of modular neural networks using Interval Type-2 Fuzzy logic

In this paper a fuzzy logic approach to determine the relevance of each module in modular neural networks for images recognition is presented. The tests were made with Type-1 and Interval Type-2 Fuzzy Inference Systems, to compare the performance of the proposed approach. In both cases the fusion operator for the modules is the Sugeno Integral, and the estimated parameters are the fuzzy densities.