Место издания:Association for Intelligent Machinery Atlantic City, NJ
Первая страница:908
Последняя страница:911
Аннотация:Recently we have proposed an algorithm of hierarchical neural network classifiers (HNNC) construction based on a modification of error backpropagation. It combines supervised learning with self-organization. Recursive use of the algorithm results in creation of compact and computationally effective self-organized structures of neural classifiers. In this paper the above algorithm is expanded for unsupervised analysis of dynamic objects, described by time series. The algorithm performs segmentation of the analyzed time-series into parts characterized by different types of dynamics. The algorithm has been successfully tested on pseudo-chaotic maps.