Research of Dynamic Competitive Learning in Neural Networks

Introduce a method of generation of new units within a cluster and a algorithm of generating new clusters. The model automatically builds up its dynamically growing in ternal representation structure during the learning process. Comparing model with other typical classification algorithm such as the Kohonen‘s self-organizing map. the model realizes a multilevel classification of the input pattern with an optional accuracy and gives a strong support possibility for the parallel computational main processor. The idea is suitable for the high-level storage of complex datas structures for object recognition.

Research of dynamic competitive learning in neural networks

Introduce a method of generation of new units within a cluster and a algorithm of generating new clusters. The model automatically builds up its dynamically growing internal representation structure during the learning process. Comparing model with other typical classification algorithm such as the Kohonen's self-organizing map, the model realizes a multilevel classification of the input pattern with an optional accuracy and gives a strong support possibility for the parallel computational main processor. The idea is suitable for the high-level storage of complex datas structures for object recognition. Foundation item: Supported by the National “Fifteenth-Year Plan” Key Project (2001BA307B01-02-01) Biography: PAN Hao (1964-), male, Ph. D, Associate professor, research direction: computational intelligence.