Characterization and Compensation of Network-Level Anomalies in Mixed-Signal Neuromorphic Modeling Platforms

↓ Direkt till sidans innehåll
↓ Direkt till sidans sekundära innehåll (sidomenyn)

Search: id:"swepub:oai:DiVA.org:kth-156452" > Characterization an...

1 of 1
Previous record
Next record
To hitlist

Details
MARC

Petrovici, Mihai A. (author)

Characterization and Compensation of Network-Level Anomalies in Mixed-Signal Neuromorphic Modeling Platforms

Article/chapterEnglish2014

Publisher, publication year, extent ...

2014-10-10
Public Library of Science (PLoS),2014
printrdacarrier

Numbers

LIBRIS-ID:oai:DiVA.org:kth-156452
https://urn.kb.se/resolve?urn=urn:nbn:se:kth:diva-156452URI
https://doi.org/10.1371/journal.pone.0108590DOI
https://urn.kb.se/resolve?urn=urn:nbn:se:su:diva-109977URI

Supplementary language notes

Language:English
Summary in:English

Part of subdatabase

SwePubSwePub

Classification

Subject category:ref swepub-contenttype
Subject category:art swepub-publicationtype

Notes

QC 20141201
AuthorCount:12;
Advancing the size and complexity of neural network models leads to an ever increasing demand for computational resources for their simulation. Neuromorphic devices offer a number of advantages over conventional computing architectures, such as high emulation speed or low power consumption, but this usually comes at the price of reduced configurability and precision. In this article, we investigate the consequences of several such factors that are common to neuromorphic devices, more specifically limited hardware resources, limited parameter configurability and parameter variations due to fixed-pattern noise and trial-to-trial variability. Our final aim is to provide an array of methods for coping with such inevitable distortion mechanisms. As a platform for testing our proposed strategies, we use an executable system specification (ESS) of the BrainScaleS neuromorphic system, which has been designed as a universal emulation back-end for neuroscientific modeling. We address the most essential limitations of this device in detail and study their effects on three prototypical benchmark network models within a well-defined, systematic workflow. For each network model, we start by defining quantifiable functionality measures by which we then assess the effects of typical hardware-specific distortion mechanisms, both in idealized software simulations and on the ESS. For those effects that cause unacceptable deviations from the original network dynamics, we suggest generic compensation mechanisms and demonstrate their effectiveness. Both the suggested workflow and the investigated compensation mechanisms are largely back-end independent and do not require additional hardware configurability beyond the one required to emulate the benchmark networks in the first place. We hereby provide a generic methodological environment for configurable neuromorphic devices that are targeted at emulating large-scale, functional neural networks.

Subject headings and genre

NATURVETENSKAP Data- och informationsvetenskap Bioinformatik hsv//swe
NATURAL SCIENCES Computer and Information Sciences Bioinformatics hsv//eng
NATURVETENSKAP Data- och informationsvetenskap hsv//swe
NATURAL SCIENCES Computer and Information Sciences hsv//eng

Added entries (persons, corporate bodies, meetings, titles ...)

Vogginger, Bernhard (author)
Mueller, Paul (author)
Breitwieser, Oliver (author)
Lundqvist, MikaelStockholms universitet,KTH,Beräkningsbiologi, CB,Numerisk analys och datalogi (NADA)(Swepub:kth)u1ogwo28 (author)
Muller, Lyle (author)
Ehrlich, Matthias (author)
Destexhe, Alain (author)
Lansner, AndersStockholms universitet,KTH,Beräkningsbiologi, CB,Numerisk analys och datalogi (NADA)(Swepub:su)lansn (author)
Schueffny, Rene (author)
Schemmel, Johannes (author)
Meier, Karlheinz (author)
KTHBeräkningsbiologi, CB (creator_code:org_t)

Related titles

In:PLOS ONE: Public Library of Science (PLoS)9:10, s. e108590-1932-6203

Internet link

Find in a library

PLOS ONE (Search for host publication in LIBRIS)

To the university's database

1 of 1
Previous record
Next record
To hitlist

Find more in SwePub

By the author/editor: Petrovici, Mihai ...; Vogginger, Bernh ...; Mueller, Paul; Breitwieser, Oli ...; Lundqvist, Mikae ...; Muller, Lyle; show more...; Ehrlich, Matthia ...; Destexhe, Alain; Lansner, Anders; Schueffny, Rene; Schemmel, Johann ...; Meier, Karlheinz; show less...

About the subject

NATURAL SCIENCES: NATURAL SCIENCES; and Computer and Inf ...; and Bioinformatics

NATURAL SCIENCES: NATURAL SCIENCES; and Computer and Inf ...

Articles in the publication: PLOS ONE

By the university: Royal Institute of Technology; Stockholm University

Search outside SwePub

Extend your search to:: Google; Google Book Search; Google Scholar

Kungliga biblioteket hanterar dina personuppgifter i enlighet med EU:s dataskyddsförordning (2018), GDPR. Läs mer om hur det funkar här.
Så här hanterar KB dina uppgifter vid användning av denna tjänst.

LIBRIS.kb.se