A Convolutional Fuzzy Neural Network for Image Classification

摘要

A model of Convolutional Fuzzy Neural Network for real world objects and scenes images classification is proposed. The Convolutional Fuzzy Neural Network consists of convolutional, pooling and fully-connected layers and a Fuzzy Self Organization Layer. The model combines the power of convolutional neural networks and fuzzy logic and is capable of handling uncertainty and impreciseness in the input pattern representation. The Training of The Convolutional Fuzzy Neural Network consists of three independent steps for three components of the net.