High Order Orthogonal Tensor Networks: Information Capacity and Reliability

Donald C. Wunsch, Missouri University of Science and Technology
Y. M. Mirkes
Alexander N. Gorban

This document has been relocated to http://scholarsmine.mst.edu/ele_comeng_facwork/1658

There were 4 downloads as of 28 Jun 2016.


Neural networks based on construction of orthogonal projectors in the tensor power of space of signals are described. A sharp estimate of their ultimate information capacity is obtained. The number of stored prototype patterns (prototypes) can many times exceed the number of neurons. A comparison with the error control codes is made