(1 + ∞)-dimensional attractor neural networks

DOI10.1088/0305-4470/33/33/301MaRDI QIDQ4520668zbMATH OpenOpenAlexFDO

Authors Nikos S. Skantzos, A. C. C. Coolen

Publication date 13 December 2000

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/0003175

zbMATH Keywords

attractor neural network modelsBoltzmann-type equilibriuminfinite-range interactionsnearest-neighbour interactionsparallel dynamicsPeretto-type equilibriumsequential Glauber dynamics

Mathematics Subject Classification ID

Dynamical systems in biology (37N25) Neural nets applied to problems in time-dependent statistical mechanics (82C32) Neural networks for/in biological studies, artificial life and related topics (92B20)

Abstract: We solve a class of attractor neural network models with a mixture of 1D nearest-neighbour and infinite-range interactions, which are of a Hebbian-type form. Our solution is based on a combination of mean-field methods, transfer matrices and 1D random-field techniques, and is obtained for Boltzmann-type equilibrium (following sequential Glauber dynamics) and Peretto-type equilibrium (following parallel dynamics). Competition between the alignment forces mediated via short-range interactions, and those mediated via infinite-range ones, is found to generate novel phenomena, such as multiple locally stable `pure' states, first-order transitions between recall states, 2-cycles and non-recall states, and domain formation leading to extremely long relaxation times. We test our results against numerical simulations and simple benchmark cases and find excellent agreement.

Recommendations

• Attractor modulation and proliferation in (1+)-dimensional neural networks
• Attractors of Hopfield-type lattice models with increasing neuronal input
• Finite connectivity attractor neural networks
• Feed-forward chains of recurrent attractor neural networks near saturation
• Attractor neural networks with excitatory neurons and fast inhibitory interneurons at low spike rates

Cited in

(6)

• 1D three-state mean-field Potts model with first- and second-order phase transitions
• Attractor modulation and proliferation in (1+)-dimensional neural networks
• Feed-forward chains of recurrent attractor neural networks near saturation
• Finite connectivity attractor neural networks
• Stationary states of a spherical minority game with ergodicity breaking
• Exact results for the Ising model on a small-world network

This page was built for publication: (1 + ∞)-dimensional attractor neural networks

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q4520668)