Title :
High order orthogonal tensor networks: information capacity and reliability
Author :
Gorban, Alexander N. ; Mirkes, Yeugenii M. ; Wunsch, Donald C., II
Author_Institution :
Krasnoyarsk State Univ., Russia
Abstract :
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
Keywords :
error correction codes; neural nets; reliability; tensors; error control codes; high order orthogonal tensor networks; information capacity; orthogonal projectors; reliability; stored prototype patterns; Computational intelligence; Computer networks; Electronic mail; Laboratories; Neurons; Power engineering computing; Prototypes; Region 8; Tensile stress; Vectors;
Conference_Titel :
Neural Networks,1997., International Conference on
Conference_Location :
Houston, TX
Print_ISBN :
0-7803-4122-8
DOI :
10.1109/ICNN.1997.616224
