A neuromorphic network for generic multivariate data classification

Schmuker, Michael, Pfeil, Thomas and Nawrot, Martin Paul (2014) A neuromorphic network for generic multivariate data classification. Proceedings of the National Academy of Sciences of the United States of America, 111 (6). pp. 2081-2086. ISSN 0027-8424

Full text not available from this repository.

Abstract

Computational neuroscience has uncovered a number of computational principles used by nervous systems. At the same time, neuromorphic hardware has matured to a state where fast silicon implementations of complex neural networks have become feasible. En route to future technical applications of neuromorphic computing the current challenge lies in the identification and implementation of functional brain algorithms. Taking inspiration from the olfactory system of insects, we constructed a spiking neural network for the classification of multivariate data, a common problem in signal and data analysis. In this model, real-valued multivariate data are converted into spike trains using "virtual receptors" (VRs). Their output is processed by lateral inhibition and drives a winner-take-all circuit that supports supervised learning. VRs are conveniently implemented in software, whereas the lateral inhibition and classification stages run on accelerated neuromorphic hardware. When trained and tested on real-world datasets, we find that the classification performance is on par with a naïve Bayes classifier. An analysis of the network dynamics shows that stable decisions in output neuron populations are reached within less than 100 ms of biological time, matching the time-to-decision reported for the insect nervous system. Through leveraging a population code, the network tolerates the variability of neuronal transfer functions and trial-to-trial variation that is inevitably present on the hardware system. Our work provides a proof of principle for the successful implementation of a functional spiking neural network on a configurable neuromorphic hardware system that can readily be applied to real-world computing problems.

Item Type: Article
Schools and Departments: School of Engineering and Informatics > Informatics
Subjects: Q Science
Depositing User: michael Schmuker
Date Deposited: 23 Sep 2014 10:25
Last Modified: 23 Sep 2014 10:25
URI: http://sro.sussex.ac.uk/id/eprint/50191
📧 Request an update