Algorithm for mapping multilayer BP networks onto the SpiNNaker neuromorphic hardware

X. Jin, M. Luján, M. M. Khan, Luis A. Plana, A. D. Rast, S. R. Welbourne, S. B. Furber

Research output: Chapter in Book/Report/Conference proceedingConference contributionpeer-review

177 Downloads (Pure)

Abstract

This paper demonstrates the feasibility and evaluates the performance of using the SpiNNaker neuromorphic hardware to simulate traditional non-spiking multi-layer per-ceptron networks with the backpropagation learning rule. In addition to investigating the mapping of checker-boarding partitioning scheme onto SpiNNaker, we propose a new algorithm called pipelined checker-boarding partitioning which introduces a pipelined mode and captures the parallelism within each partition of the weight matrix, allowing the overlapping of communication and computation. Not only does the proposed algorithm localize communication, but it can also hide a part of or even all the communication. The performance is evaluated with SpiNNaker configurations up to 1000 nodes (20000 cores). © 2010 IEEE.
Original languageEnglish
Title of host publication9th International Symposium on Parallel and Distributed Computing, ISPDC 2010|Int. Symp. Parallel Distrib. Comput., ISPDC
Place of PublicationUSA
PublisherIEEE
Pages9-16
Number of pages7
ISBN (Print)9780769541204
DOIs
Publication statusPublished - 2010
Event9th International Symposium on Parallel and Distributed Computing, ISPDC 2010 - Istanbul
Duration: 1 Jul 2010 → …

Conference

Conference9th International Symposium on Parallel and Distributed Computing, ISPDC 2010
CityIstanbul
Period1/07/10 → …

Keywords

  • Backpropagation
  • Mapping
  • Parallel
  • Perceptron
  • SpiNNaker

Fingerprint

Dive into the research topics of 'Algorithm for mapping multilayer BP networks onto the SpiNNaker neuromorphic hardware'. Together they form a unique fingerprint.

Cite this