I. Introduction
A response integration method is a mechanism for combining the outputs of n modules for achieving a representative value for all the information. In this paper a new method for response integration in modular neural networks using generalized type-2 fuzzy logic is presented. The main idea is that generalized type-2 fuzzy logic can manage higher degrees of uncertainty than interval type-2and type-1 fuzzy logic, and as a consequence response integration can be done in a better way.