Toggle Main Menu Toggle Search

Open Access padlockePrints

Connection-centric network for spiking neural networks

Lookup NU author(s): Robin Emery, Professor Alex Yakovlev, Dr Graeme Chester

Downloads


Abstract

A reconfigurable network architecture applied to spiking neural networks is presented. For hardware platforms for neural networks that implement some degree of realism of interest to neuroscientists, connectivity between neurons can be a major limitation. Recent data indicates that neurons in the brain form clusters of connections. Through the combination of this data and a routing scheme that uses a hybrid of short-range direct connectivity and an AER (Address Event Representation) network, the presented architecture aims to provide a useful amount of inter-neuron connectivity. A connection-centric design can provide opportunities for NoCs such as optimising power bandwidth or introducing redundancy. A method of mapping a network to the architecture is discussed, along with results of optimal hardware specifications for a given set of network parameters.


Publication metadata

Author(s): Emery R, Yakovlev A, Chester G

Publication type: Conference Proceedings (inc. Abstract)

Publication status: Published

Conference Name: 3rd ACM/IEEE International Symposium on Networks-on-Chip (NoCS 2009)

Year of Conference: 2009

Pages: 144-152

Date deposited: 24/05/2010

Publisher: IEEE

URL: http://dx.doi.org/10.1109/NOCS.2009.5071462

DOI: 10.1109/NOCS.2009.5071462

Library holdings: Search Newcastle University Library for this item

ISBN: 9781424441426


Share