Electronic implementation of an analogue attractor neural network with stochastic learning

We describe and discuss an electronic implementation of an attractor neural network with plastic synapses. The network undergoes double dynamics, for the neurons as well as the synapses. Both dynamical processes are unsupervised. The synaptic dynamics is autonomous, in that it is driven exclusively and perpetually by neural activities. The latter follow the network activity via the developing synapses and the influence of external stimuli. Such a network self-organizes and is a device which converts the gross statistical characteristics of the stimulus input stream into a set of attractors (reverberations). To maintain for long time the acquired memory, the analog synaptic efficacies are discretized by a stochastic refresh mechanism. The discretized synaptic memory has indefinitely long lifetime in the absence of activity in the network. It is modified only by the arrival of new stimuli. The stochastic refresh mechanism produces transitions at low probability which ensures that transient stimuli do not cr...

[1]  Nicolas Brunel,et al.  Learning internal representations in an attractor neural network with analogue neurons , 1995 .

[2]  D. Amit,et al.  Constraints on learning in dynamic synapses , 1992 .

[3]  Ki-Hwan Ahn,et al.  Implementation of Million Connections Neural Hardware with URAN-I , 1993 .

[4]  T G Clarkson,et al.  The pRAM: an adaptive VLSI chip , 1993, IEEE Trans. Neural Networks.

[5]  Stuart Haber,et al.  A VLSI-efficient technique for generating multiple uncorrelated noise sources and its application to stochastic neural networks , 1991 .

[6]  H.P. Graf,et al.  A reconfigurable CMOS neural network , 1990, 1990 37th IEEE International Conference on Solid-State Circuits.

[7]  J. Fuster.  Behavioral electrophysiology of the prefrontal cortex , 1984, Trends in Neurosciences.

[8]  Daniel J. Amit,et al.  Learning in Neural Networks with Material Synapses , 1994, Neural Computation.

[9]  Nicolas Brunel,et al.  Adequate input for learning in attractor neural networks , 1993 .

[10]  Davide Badoni,et al.  LANN27: an electronic implementation of an analog attractor neural network with stochastic learning , 1995, SPIE Defense + Commercial Sensing.

[11]  Robert B. Allen,et al.  Stochastic Learning Networks and their Electronic Implementation , 1987, NIPS.

[12]  Davide Badoni,et al.  Learning Attractor Neural Network: The Electronic Implementation , 1992, Int. J. Neural Syst..

[13]  B L McNaughton,et al.  Dynamics of the hippocampal ensemble code for space. , 1993, Science.

[14]  Temporal Pattern Dependent Spatial-Distribution of LTP in the Hippocampal CA1 Area Studied by an Optical Imaging Method , 1994 .

[15]  Daniel J. Amit,et al.  Constraints on learning in dynamic synapses , 1992, Network: Computation in Neural Systems.

[16]  Y. Tamura,et al.  A BiCMOS analog neural network with dynamically updated weights , 1992, 1990 37th IEEE International Conference on Solid-State Circuits.

[17]  Paul L. Meyer,et al.  Introductory Probability and Statistical Applications , 1970 .

[18]  José Luis Huertas,et al.  A CMOS analog adaptive BAM with on-chip learning and weight refreshing , 1993, IEEE Trans. Neural Networks.

[19]  Daniel J. Amit,et al.  Quantitative Study of Attractor Neural Network Retrieving at Low Spike Rates: I , 1991 .

[20]  Ulrich Ramacher.  SYNAPSE - A Neurocomputer that Synthesizes Neural Algorithms on a Parallel Systolic Engine , 1992, J. Parallel Distributed Comput..

[21]  B. McNaughton,et al.  Hebb-Marr networks and the neurobiological representation of action in space. , 1990 .

[22]  J. Hopfield,et al.  Dynamic properties of neural networks with adapting synapses , 1992 .

[23]  R. Muller,et al.  Functional organization of the hippocampal CA3 region: implications for epilepsy, brain waves and spatial behaviour , 1992 .

[24]  A. A. Abidi,et al.  An Analog CMOS Backward Error-propagation LSI , 1988, Twenty-Second Asilomar Conference on Signals, Systems and Computers.

[25]  Robert M. Kozelka,et al.  Introductory Probability and Statistical Applications. , 1966 .

[26]  J. Fuster.  Unit activity in prefrontal cortex during delayed-response performance: neuronal correlates of transient memory. , 1973, Journal of neurophysiology.

[27]  E T Rolls,et al.  Computational constraints suggest the need for two distinct input systems to the hippocampal CA3 network , 1992, Hippocampus.

[28]  J J Hopfield,et al.  Neurons with graded response have collective computational properties like those of two-state neurons. , 1984, Proceedings of the National Academy of Sciences of the United States of America.

[29]  Carver Mead,et al.  Analog VLSI and neural systems , 1989 .

[30]  Y. Miyashita,et al.  Neuronal correlate of pictorial short-term memory in the primate temporal cortexYasushi Miyashita , 1988, Nature.

[31]  E. Rolls.  Functions of neuronal networks in the hippocampus and neocortex in memory , 1989 .