Efficiency analysis of solution of classification using hybrid Kohonen neural networks

The results of solution of classification using standard hybrid kohonen neural network and modifications of this model created by authors - composite, distributed and fuzzy hybrid kohonen neural network were obtained in this paper. Researches were performed on dataset models from UCI repository. Neural networks’ structures and teaching algoritms were described. The efficiency of neural networks based on two criterions: classification error and neurons number in network when minimum classification error was archived was researched.