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