The modified self-organizing fuzzy neural network model for adaptability evaluation

The author proposed a novel approach for evolving the architecture of a multi-layer neural network based on neural network and fuzzy logic technologies. The model is front-network which comprised with five layers architecture which composed of dynamic inference of fuzzy rules where the consequent sub-models are implemented by recurrent neural networks with internal feedback paths and dynamic neuron synapses. An optimal learning scheme with the evaluation guide line which error data embed is applied for training of LF-DFNN models. The results of experiment demonstrate that new model have superior performance.