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
D. C. Wunsch et al., "High Order Orthogonal Tensor Networks: Information Capacity and Reliability," Proceedings of the International Conference on Neural Networks,1997, Institute of Electrical and Electronics Engineers (IEEE), Jan 1997.
The definitive version is available at http://dx.doi.org/10.1109/ICNN.1997.616224
International Conference on Neural Networks,1997
Electrical and Computer Engineering
Keywords and Phrases
Error Control Codes; Error Correction Codes; High Order Orthogonal Tensor Networks; Information Capacity; Neural Nets; Orthogonal Projectors; Reliability; Stored Prototype Patterns; Tensors
Article - Conference proceedings
© 1997 Institute of Electrical and Electronics Engineers (IEEE), All rights reserved.