Estimation of Performance of the Hopfield Randomized Memory

  • Authors:

  • B. V. Kryzhanovskii;V. N. Koshelev;A. B. Fonarev

  • Affiliations:

  • -;-;-

  • Venue:
  • Problems of Information Transmission
  • Year:
  • 2001

Quantified Score

Hi-index 0.00

Visualization

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.