WIAS Preprint No. 105, (1994)

Self-averaging in a class of generalized Hopfield models


Authors

  • Bovier, Anton

2010 Mathematics Subject Classification

  • 60K35 82C32

Keywords

  • Hopfield model, neural networks, self-averaging, law of large numbers

DOI

10.20347/WIAS.PREPRINT.105

Abstract

We prove the almost sure convergence to zero of the fluctuations of the free energy, resp. local free energies, in a class of disordered mean-field spin systems that generalize the Hopfield model in two ways: 1) Multi-spin interactions are permitted and 2) the random variables ξμi i describing the "patterns" can have arbitrary distributions with mean zero and finite 4+∈-th moments. The number of patterns, M, is allowed to be an arbitrary multiple of the systemsize. This generalizes a previous result of Bovier, Gayrard, and Picco [BGP3] for the standard Hopfield model, and improves a result of Feng and Tirozzi [FT] that required M to be a finite constant. Note that the convergence of the mean of the free energy is not proven.

Appeared in

  • J. Phys. A 27 (1994), No. 21, pp. 7069-7077.

Download Documents