Learning internal representations in an attractor neural network with analogue neurons

DOI10.1088/0954-898X/6/3/004MaRDI QIDQ4851671zbMATH OpenOpenAlexFDO

Authors Daniel J. Amit, Nicolas J.-B. Brunel

Publication date 15 January 1996

Published in Network: Computation in Neural Systems (Search for Journal in Brave)

Full work available at URL https://doi.org/10.1088/0954-898x/6/3/004

zbMATH Keywords

simulationsdifferent time scalesafferent currentsexternal synaptic inputslearning attractor neural networkoutput spike ratesunsupervised, analogue Hebbian process

Mathematics Subject Classification ID

Learning and adaptive systems in artificial intelligence (68T05) Neural networks for/in biological studies, artificial life and related topics (92B20)

Recommendations

• Adequate input for learning in attractor neural networks
• Slow stochastic Hebbian learning of classes of stimuli in a recurrent neural network
• scientific article; zbMATH DE number 125397

Cited in

(7)

• scientific article; zbMATH DE number 125397 (Why is no real title available?)
• Reducing a cortical network to a Potts model yields storage capacity estimates
• An autoassociative neural network model of paired-associate learning
• A hierarchical dynamical map as a basic frame for cortical mapping and its application to priming
• Adequate input for learning in attractor neural networks
• Anatomical constraints on lateral competition in columnar cortical architectures
• Modeling and estimating recall processing capacity: sensitivity and diagnostic utility in application to mild cognitive impairment

This page was built for publication: Learning internal representations in an attractor neural network with analogue neurons

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q4851671)