Probing the basins of attraction of a recurrent neural network

DOI10.1088/0305-4470/33/9/304zbMATH Open0969.82022arXivcond-mat/0002358OpenAlexW2131515048MaRDI QIDQ4495992FDOQ4495992

Authors: M. Heerema, W. A. van Leeuwen 

Publication date: 13 August 2000

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

Abstract: A recurrent neural network is considered that can retrieve a collection of patterns, as well as slightly perturbed versions of this `pure' set of patterns via fixed points of its dynamics. By replacing the set of dynamical constraints, i.e., the fixed point equations, by an extended collection of fixed-point-like equations, analytical expressions are found for the weights w_ij(b) of the net, which depend on a certain parameter b. This so-called basin parameter b is such that for b=0 there are, a priori, no perturbed patterns to be recognized by the net. It is shown by a numerical study, via probing sets, that a net constructed to recognize perturbed patterns, i.e., with values of the connections w_ij(b) with b unequal zero, possesses larger basins of attraction than a net made with the help of a pure set of patterns, i.e., with connections w_ij(b=0). The mathematical results obtained can, in principle, be realized by an actual, biological neural net.

Full work available at URL: https://arxiv.org/abs/cond-mat/0002358

Recommendations

• scientific article; zbMATH DE number 4092811
• A recurrent neural network with ever changing synapses
• Stability and attractivity in associative memory networks
• Retrieval properties of diluted attractor neural networks
• scientific article; zbMATH DE number 843144

Mathematics Subject Classification ID

Dynamical systems in other branches of physics (quantum mechanics, general relativity, laser physics) (37N20) Neural nets applied to problems in time-dependent statistical mechanics (82C32)

Cited In (5)

• A numerical study of basins of attraction of zero-finding neural nets designed using control theory
• Title not available (Why is that?)
• Arbitrary sensitive transitions in recurrent neural networks
• Title not available (Why is that?)
• Estimation of the basin of attractions in CNNs

This page was built for publication: Probing the basins of attraction of a recurrent neural network

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q4495992)