Classification of Correlated Patterns with a Configurable Analog VLSI Neural Network of Spiking Neurons and Self-Regulating Plastic Synapses
- 1 November 2009
- journal article
- research article
- Published by MIT Press in Neural Computation
- Vol. 21 (11), 3106-3129
- https://doi.org/10.1162/neco.2009.08-07-599
Abstract
We describe the implementation and illustrate the learning performance of an analog VLSI network of 32 integrate-and-fire neurons with spike-frequency adaptation and 2016 Hebbian bistable spike-driven stochastic synapses, endowed with a self-regulating plasticity mechanism, which avoids unnecessary synaptic changes. The synaptic matrix can be flexibly configured and provides both recurrent and external connectivity with address-event representation compliant devices. We demonstrate a marked improvement in the efficiency of the network in classifying correlated patterns, owing to the self-regulating mechanism.Keywords
This publication has 22 references indexed in Scilit:
- Learning Real-World Stimuli in a Neural Network with Spike-Driven Synaptic DynamicsNeural Computation, 2007
- Communicating Neuronal Ensembles between Neuromorphic ChipsPublished by Springer Science and Business Media LLC ,2007
- A Multichip Pulse-Based Neuromorphic Infrastructure and Its Application to a Model of Orientation SelectivityIEEE Transactions on Circuits and Systems I: Regular Papers, 2007
- An aVLSI recurrent network of spiking neurons with reconfigurable and plastic synapsesPublished by Institute of Electrical and Electronics Engineers (IEEE) ,2006
- Modelling the formation of working memory with networks of integrate-and-fire neurons connected by plastic synapsesJournal of Physiology-Paris, 2003
- A vlsi recurrent network of integrate-and-fire neurons connected by plastic synapses with long-term memoryIEEE Transactions on Neural Networks, 2003
- Spike-Driven Synaptic Dynamics Generating Working Memory StatesNeural Computation, 2003
- Hebbian spike-driven synaptic plasticity for learning patterns of mean firing ratesBiological Cybernetics, 2002
- Generalizing with perceptrons in the case of structured phase- and pattern-spacesJournal of Physics A: General Physics, 1998
- Learning in Neural Networks with Material SynapsesNeural Computation, 1994