Robust Classification of Correlated Patterns with a Neuromorphic VLSI Network of Spiking Neurons

Mitra, S., Indiveri, G. and Fusi, S. (2007) Robust Classification of Correlated Patterns with a Neuromorphic VLSI Network of Spiking Neurons. In: IEEE Biomedical Circuits and Systems Conference (BIOCAS 2007), Montreal, Canada, 27-30 Nov 2007, pp. 87-90. ISBN 9781424415243 (doi: 10.1109/BIOCAS.2007.4463315)

Full text not currently available from Enlighten.

Abstract

We demonstrate robust classification of correlated patterns of mean firing rates, using a VLSI network of spiking neurons and spike-driven plastic synapses. The synapses have bistable weights over long time-scales and the transitions from one stable state to the other are driven by the pre and postsynaptic spiking activity. Learning is supervised by a teacher signal which provides an extra current to the output neurons during the training phase. This current steers the activity of the neurons toward the desired value, and the synaptic weights are modified only if the current generated by the plastic synapses does not match the one provided by the teacher signal. If the neuron's response matches the desired output, the synaptic updates are blocked. Such a feature allows the neurons to classify spatial patterns of mean firing rates, even when they have significant correlations. If synaptic updates are stochastic, as in the case of random Poisson input spike trains, the classification performance can be further improved by combining the outcome of multiple neurons together.

Item Type:Conference Proceedings
Status:Published
Refereed:Yes
Glasgow Author(s) Enlighten ID:Mitra, Dr Srinjoy
Authors: Mitra, S., Indiveri, G., and Fusi, S.
College/School:College of Science and Engineering > School of Engineering
ISBN:9781424415243

University Staff: Request a correction | Enlighten Editors: Update this record