Thresholds in layered neural networks with variable activity

DOI10.1088/0305-4470/33/14/301MaRDI QIDQ4507641zbMATH OpenOpenAlexFDO

Authors D. Bollé, G. Massolo

Publication date 8 October 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/9909443

Mathematics Subject Classification ID

Learning and adaptive systems in artificial intelligence (68T05) Software, source code, etc. for problems pertaining to statistical mechanics (82-04) Neural networks for/in biological studies, artificial life and related topics (92B20) Neural nets applied to problems in time-dependent statistical mechanics (82C32)

Abstract: The inclusion of a threshold in the dynamics of layered neural networks with variable activity is studied at arbitrary temperature. In particular, the effects on the retrieval quality of a self-controlled threshold obtained by forcing the neural activity to stay equal to the activity of the stored paterns during the whole retrieval process, are compared with those of a threshold chosen externally for every loading and every temperature through optimisation of the mutual information content of the network. Numerical results, mostly concerning low activity networks are discussed.

Recommendations

• scientific article; zbMATH DE number 2095944
• Dynamical properties of a randomly diluted neural network with variable activity
• Variable threshold as a model for selective attention, (de)sensitization, and anesthesia in associative neural networks
• Mutual information and self-control of a fully-connected low-activity neural network
• Hopfield model with a dynamic threshold

Cited in

(8)

• Sparse coding for layered neural networks
• scientific article; zbMATH DE number 2095944 (Why is no real title available?)
• Information flow in layered networks of non-monotonic units
• Dynamical properties of a randomly diluted neural network with variable activity
• On the Computational Power of Threshold Circuits with Sparse Activity
• Variable threshold as a model for selective attention, (de)sensitization, and anesthesia in associative neural networks
• Dirac distributions and threshold firing in neural networks
• Mutual information and self-control of a fully-connected low-activity neural network

This page was built for publication: Thresholds in layered neural networks with variable activity

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q4507641)