%0 Journal Article %T Method of Parallel-Hierarchical Network Self-Training and its Application for Pattern Classification and Recognition %A TIMCHENKO %A L. %A KOKRIATSKAIA %A N. %A MELNIKOV %A V. %A MAKARENKO %A R. %J Advances in Electrical and Computer Engineering %D 2012 %I Stefan cel Mare University of Suceava %R 10.4316/aece.2012.04006 %X Propositions necessary for development of parallel-hierarchical (PH) network training methods are discussed in this article. Unlike already known structures of the artificial neural network, where non-normalized (absolute) similarity criteria are used for comparison, the suggested structure uses a normalized criterion. Based on the analysis of training rules, a conclusion is made that application of two training methods with a teacher is optimal for PH network training: error correction-based training and memory-based training. Mathematical models of training and a combined method of PH network training for recognition of static and dynamic patterns are developed. %K parallel-hierarchical network %K training %K population coding %K preparation %K face recognition %U http://dx.doi.org/10.4316/AECE.2012.04006