|
Problemy Peredachi Informatsii, 2001, Volume 37, Issue 2, Pages 77–87
(Mi ppi518)
|
|
|
|
Large Systems
Estimation of Performance of the Hopfield Randomized Memory
B. V. Kryzhanovskii, V. N. Koshelev, A. B. Fonarev
Abstract:
We study the recognition capability of a Hopfield network, i.e., a neural network where interaction of nodes is determined by the Hebb transform. We present a formally rigorous derivation of an upper bound on the error probability for recognition of randomized objects. It is based on the standard technique of estimating large deviations by the Chebyshev–Chernov method.
Received: 13.10.2000
Citation:
B. V. Kryzhanovskii, V. N. Koshelev, A. B. Fonarev, “Estimation of Performance of the Hopfield Randomized Memory”, Probl. Peredachi Inf., 37:2 (2001), 77–87; Problems Inform. Transmission, 37:2 (2001), 155–164
Linking options:
https://www.mathnet.ru/eng/ppi518 https://www.mathnet.ru/eng/ppi/v37/i2/p77
|
Statistics & downloads: |
Abstract page: | 296 | Full-text PDF : | 91 | References: | 36 |
|