Abstracts

Programmirung

A class of artificial algebraic Sigma Pi --neurons with input layer of adaptive functional units and without and with different types of inputs and output is considered. A general scheme for recurrent learning of Sigma Pi --neurons with minimizing of product's rank in polylinear forms is proposed. The learning performs on the bases of ordered sequences of input vectors. The minimization technique allow in many cases to decrease essentially the complexity of hardware implementation and the complexity of evaluation Sigma Pi --neurons in sequential and sequential--parallel implementation.

Full Text in Russian:

HTML

Note. Abstracts are published in author's edition

Comments

[Home] [Conference]

©2001, Siberian Branch of Russian Academy of Science, Novosibirsk
©2001, United Institute of Computer Science SB RAS, Novosibirsk
©2001, Institute of Computational Techologies SB RAS, Novosibirsk
©2001, A.P. Ershov Institute of Informatics Systems SB RAS, Novosibirsk
©2001, Institute of Mathematics SB RAS, Novosibirsk
©2001, Institute of Cytology and Genetics SB RAS, Novosibirsk
©2001, Institute of Computational Mathematics and Mathematical Geophysics SB RAS, Novosibirsk
©2001, Novosibirsk State University
Last modified 06-Jul-2012 (11:45:21)