Retrieval phase diagrams of non-monotonic Hopfield networks

DOI10.1088/0305-4470/29/16/008zbMATH Open0897.68084arXivcond-mat/9604065OpenAlexW3099372094MaRDI QIDQ4390218FDOQ4390218

Authors: Jun-Ichi Inoue 

Publication date: 30 September 1998

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

Abstract: We investigate the retrieval phase diagrams of an asynchronous fully-connected attractor network with non-monotonic transfer function by means of a mean-field approximation. We find for the noiseless zero-temperature case that this non-monotonic Hopfield network can store more patterns than a network with monotonic transfer function investigated by Amit et al. Properties of retrieval phase diagrams of non-monotonic networks agree with the results obtained by Nishimori and Opris who treated synchronous networks. We also investigate the optimal storage capacity of the non-monotonic Hopfield model with state-dependent synaptic couplings introduced by Zertuche et el. We show that the non-monotonic Hopfield model with state-dependent synapses stores more patterns than the conventional Hopfield model. Our formulation can be easily extended to a general transfer function.

Full work available at URL: https://arxiv.org/abs/cond-mat/9604065

Recommendations

• Retrieval phase diagrams for attractor neural networks with optimal interactions
• Retrieval via non-equilibrium states in neural networks
• Retrieval and chaos in extremely diluted non-monotonic neural networks
• The retrieval phase of the Hopfield model: A rigorous analysis of the overlap distribution
• Application of two-parameter dynamical replica theory to retrieval dynamics of associative memory with non-monotonic neurons
• Retrieval Properties of Hopfield and Correlated Attractors in an Associative Memory Model
• Effects of pattern bias on retrieval dynamics in and Hopfield networks

zbMATH Keywords

retrieval phase diagrams

Mathematics Subject Classification ID

Learning and adaptive systems in artificial intelligence (68T05) Dynamics of random walks, random surfaces, lattice animals, etc. in time-dependent statistical mechanics (82C41)

Cited In (13)

• Onset of 'super retrieval phase' and enhancement of the storage capacity in neural networks of nonmonotonic neurons
• Information flow in layered networks of non-monotonic units
• Retrieval phase diagrams for attractor neural networks with optimal interactions
• Title not available (Why is that?)
• Retrieval via non-equilibrium states in neural networks
• Exponential stability in Hopfield-type neural networks with impulses
• Nonlinear neural networks. II: Information processing.
• Retrieval and chaos in extremely diluted non-monotonic neural networks
• Layered neural networks with non-monotonic transfer functions
• Exponential decay for a system of equations with distributed delays
• Halanay inequality with Hadamard derivative and application to a neural network system
• Title not available (Why is that?)
• Non-linear neural networks with external noise

This page was built for publication: Retrieval phase diagrams of non-monotonic Hopfield networks

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q4390218)