Learning internal representations in an attractor neural network with analogue neurons
- 1 January 1995
- journal article
- Published by Taylor & Francis in Network: Computation in Neural Systems
- Vol. 6 (3) , 359-388
- https://doi.org/10.1088/0954-898x_6_3_004
Abstract
A learning attractor neural network (LANN) with a double dynamics of neural activities and synaptic efficacies, operating on two different timescales is studied by simulations in preparation for an electronic implementation, The present network includes several quasi-realistic features: neurons are represented by their afferent currents and output spike rates; excitatory and inhibitory neurons are separated; attractor spike rates as well as coding levels in arriving stimuli are low; learning takes place only between excitatory units. Synaptic dynamics is an unsupervised, analogue Hebbian process, but long term memory in the absence of neural activity is maintained by a refresh mechanism which on long timescales discretizes the synaptic values, converting learning into asynchronous stochastic process induced by the stimuli on the synaptic efficacies.This network is intended to lean a set of amactors from the statistics of freely arriving stimuli, which are represented by extemal synaptic inputs injected in...Keywords
This publication has 22 references indexed in Scilit:
- Electronic implementation of an analogue attractor neural network with stochastic learningNetwork: Computation in Neural Systems, 1995
- Learning in Neural Networks with Material SynapsesNeural Computation, 1994
- Adequate input for learning in attractor neural networksNetwork: Computation in Neural Systems, 1993
- Constraints on learning in dynamic synapsesNetwork: Computation in Neural Systems, 1992
- Effective neurons and attractor neural networks in cortical environmentNetwork: Computation in Neural Systems, 1992
- LEARNING ATTRACTOR NEURAL NETWORK: THE ELECTRONIC IMPLEMENTATIONInternational Journal of Neural Systems, 1992
- Neuronal Networks of the HippocampusPublished by Cambridge University Press (CUP) ,1991
- Quantitative study of attractor neural network retrieving at low spike rates: I. substrate—spikes, rates and neuronal gainNetwork: Computation in Neural Systems, 1991
- Quantitative study of attractor neural networks retrieving at low spike rates: II. Low-rate retrieval in symmetric networksNetwork: Computation in Neural Systems, 1991
- A theory for cerebral neocortexProceedings of the Royal Society of London. B. Biological Sciences, 1970