In this paper we introduce an Adaptive Neural Fuzzy Channel Equalizer (ANFCE) based on Adaptive Neural Fuzzy Filter (ANFF). The ANFF is a five layer neural network that is able to use the expert knowledge in its structure. The structure and parameters of this network are adjusted according to the training data and the available expert knowledge. At first, ANFF doesn’t have any node in its hidden layers. In this work, by applying some optimization on the adjusting parameters, output production and classification steps of ANFF algorithm, the ANFF training algorithm is improved. Experiment results show that these optimizations increase the performance of the ANFF while reduce the computational complexity.
