A multi-moment pattern recognition method based on neural networks

Proposes a fuzzy set theory to preprocess the feature of a Chinese character and uses the multi-moment method to classify the patterns in the neural network. Since it can be used in overlapping classes, this method has practical value.

[1]  Issam Dagher,et al.  Properties of learning of a Fuzzy ART Variant , 1999, Neural Networks.

[2]  Korris Fu-Lai Chung,et al.  Fuzzy competitive learning , 1994, Neural Networks.

[3]  Witold Pedrycz,et al.  Fuzzy neural networks with reference neurons as pattern classifiers , 1992, IEEE Trans. Neural Networks.