The signal-to-noise analysis of the Little–Hopfield model revisited

DOI10.1088/0305-4470/37/6/001MaRDI QIDQ4466282zbMATH OpenOpenAlexFDO

Authors D. Bollé, J. Busquets Blanco, T. Verbeiren

Publication date 9 June 2004

Published in Journal of Physics A: Mathematical and General (Search for Journal in Brave)

Full work available at URL https://arxiv.org/abs/cond-mat/0307499

Mathematics Subject Classification ID

Neural nets applied to problems in time-dependent statistical mechanics (82C32)

Abstract: Using the generating functional analysis an exact recursion relation is derived for the time evolution of the effective local field of the fully connected Little-Hopfield model. It is shown that, by leaving out the feedback correlations arising from earlier times in this effective dynamics, one precisely finds the recursion relations usually employed in the signal-to-noise approach. The consequences of this approximation as well as the physics behind it are discussed. In particular, it is pointed out why it is hard to notice the effects, especially for model parameters corresponding to retrieval. Numerical simulations confirm these findings. The signal-to-noise analysis is then extended to include all correlations, making it a full theory for dynamics at the level of the generating functional analysis. The results are applied to the frequently employed extremely diluted (a)symmetric architectures and to sequence processing networks.

Recommendations

• Theory of the dynamics of the Hopfield model of associative memory
• A new perturbation theory for the dynamics of the Little-Hopfield model
• The Little–Hopfield model on a sparse random graph
• Associative memories in infinite dimensional spaces
• Noise distributions in retrieval dynamics of the Hopfield model

Cited in

(7)

• Mean-field dynamics of sequence processing neural networks with finite connectivity
• Localized activity profiles and storage capacity of rate-based autoassociative networks
• A new perturbation theory for the dynamics of the Little-Hopfield model
• Transient dynamics for sequence processing neural networks
• The Little–Hopfield model on a sparse random graph
• Noise distributions in retrieval dynamics of the Hopfield model
• Noise removal using hysteretic Hopfield tunnelling network in message transmission systems

This page was built for publication: The signal-to-noise analysis of the Little–Hopfield model revisited

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q4466282)