Сибирский федеральный университет

Тип публикации: доклад, тезисы доклада, статья из сборника материалов конференций

Конференция: IEEE International Conference on Neural Networks; HOUSTON, TX; HOUSTON, TX

Год издания: 1997

Ключевые слова: Information theory, Mathematical operators, Tensors, Vectors, Neural networks, High order orthogonal tensor networks, Error control code, Orthogonal projectors, Orthogonal tensors, Prototype patterns, Sharp estimates

Аннотация: 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.

Журнал: 1997 IEEE INTERNATIONAL CONFERENCE ON NEURAL NETWORKS, VOLS 1-4

Номера страниц: 1311-1314

Место издания: NEW YORK

Издатель: I E E E

• Gorban A.N. (Krasnoyarsk State Technical Univ)
• Mirkes Y.M. (Krasnoyarsk State Technical Univ)
• Wunsch D.C. (Krasnoyarsk State Technical Univ)

• Web of Science Core Collection
• РИНЦ (eLIBRARY.RU)
• Scopus