6 April 1995 LANN27: an electronic implementation of an analog attractor neural network with stochastic learning
Author Affiliations +
We describe and discuss an electronic implementation of an attractor neural network with plastic synapses. The synaptic dynamics are unsupervised and autonomous, in that they are 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 a long time the acquired memory the analog synaptic efficacies are discretized by a stochastic refresh mechanism. The discretized synaptic memory has indefinitely long life time 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 create significant modifications and that the system has large palimpsestic memory. The electronic implementation is completely analog, stochastic and asynchronous. The circuitry of the first prototype is discussed in some detail as well as the tests performed on it. In carrying out the implementation we have been guided by biological considerations and by electronic constraints.
© (1995) COPYRIGHT Society of Photo-Optical Instrumentation Engineers (SPIE). Downloading of the abstract is permitted for personal use only.
Davide Badoni, Davide Badoni, Stefano Bertazzoni, Stefano Bertazzoni, Stefano Buglioni, Stefano Buglioni, Gaetano Salina, Gaetano Salina, Stefano Fusi, Stefano Fusi, Daniel J. Amit, Daniel J. Amit, "LANN27: an electronic implementation of an analog attractor neural network with stochastic learning", Proc. SPIE 2492, Applications and Science of Artificial Neural Networks, (6 April 1995); doi: 10.1117/12.205117; https://doi.org/10.1117/12.205117

Back to Top