Cargando…
Compensating Inhomogeneities of Neuromorphic VLSI Devices Via Short-Term Synaptic Plasticity
Recent developments in neuromorphic hardware engineering make mixed-signal VLSI neural network models promising candidates for neuroscientific research tools and massively parallel computing devices, especially for tasks which exhaust the computing power of software simulations. Still, like all anal...
Autores principales: | , , , , , |
---|---|
Formato: | Texto |
Lenguaje: | English |
Publicado: |
Frontiers Research Foundation
2010
|
Materias: | |
Acceso en línea: | https://www.ncbi.nlm.nih.gov/pmc/articles/PMC2965017/ https://www.ncbi.nlm.nih.gov/pubmed/21031027 http://dx.doi.org/10.3389/fncom.2010.00129 |
_version_ | 1782189461657878528 |
---|---|
author | Bill, Johannes Schuch, Klaus Brüderle, Daniel Schemmel, Johannes Maass, Wolfgang Meier, Karlheinz |
author_facet | Bill, Johannes Schuch, Klaus Brüderle, Daniel Schemmel, Johannes Maass, Wolfgang Meier, Karlheinz |
author_sort | Bill, Johannes |
collection | PubMed |
description | Recent developments in neuromorphic hardware engineering make mixed-signal VLSI neural network models promising candidates for neuroscientific research tools and massively parallel computing devices, especially for tasks which exhaust the computing power of software simulations. Still, like all analog hardware systems, neuromorphic models suffer from a constricted configurability and production-related fluctuations of device characteristics. Since also future systems, involving ever-smaller structures, will inevitably exhibit such inhomogeneities on the unit level, self-regulation properties become a crucial requirement for their successful operation. By applying a cortically inspired self-adjusting network architecture, we show that the activity of generic spiking neural networks emulated on a neuromorphic hardware system can be kept within a biologically realistic firing regime and gain a remarkable robustness against transistor-level variations. As a first approach of this kind in engineering practice, the short-term synaptic depression and facilitation mechanisms implemented within an analog VLSI model of I&F neurons are functionally utilized for the purpose of network level stabilization. We present experimental data acquired both from the hardware model and from comparative software simulations which prove the applicability of the employed paradigm to neuromorphic VLSI devices. |
format | Text |
id | pubmed-2965017 |
institution | National Center for Biotechnology Information |
language | English |
publishDate | 2010 |
publisher | Frontiers Research Foundation |
record_format | MEDLINE/PubMed |
spelling | pubmed-29650172010-10-28 Compensating Inhomogeneities of Neuromorphic VLSI Devices Via Short-Term Synaptic Plasticity Bill, Johannes Schuch, Klaus Brüderle, Daniel Schemmel, Johannes Maass, Wolfgang Meier, Karlheinz Front Comput Neurosci Neuroscience Recent developments in neuromorphic hardware engineering make mixed-signal VLSI neural network models promising candidates for neuroscientific research tools and massively parallel computing devices, especially for tasks which exhaust the computing power of software simulations. Still, like all analog hardware systems, neuromorphic models suffer from a constricted configurability and production-related fluctuations of device characteristics. Since also future systems, involving ever-smaller structures, will inevitably exhibit such inhomogeneities on the unit level, self-regulation properties become a crucial requirement for their successful operation. By applying a cortically inspired self-adjusting network architecture, we show that the activity of generic spiking neural networks emulated on a neuromorphic hardware system can be kept within a biologically realistic firing regime and gain a remarkable robustness against transistor-level variations. As a first approach of this kind in engineering practice, the short-term synaptic depression and facilitation mechanisms implemented within an analog VLSI model of I&F neurons are functionally utilized for the purpose of network level stabilization. We present experimental data acquired both from the hardware model and from comparative software simulations which prove the applicability of the employed paradigm to neuromorphic VLSI devices. Frontiers Research Foundation 2010-10-08 /pmc/articles/PMC2965017/ /pubmed/21031027 http://dx.doi.org/10.3389/fncom.2010.00129 Text en Copyright © 2010 Bill, Schuch, Brüderle, Schemmel, Maass and Meier. http://www.frontiersin.org/licenseagreement This is an open-access article subject to an exclusive license agreement between the authors and the Frontiers Research Foundation, which permits unrestricted use, distribution, and reproduction in any medium, provided the original authors and source are credited. |
spellingShingle | Neuroscience Bill, Johannes Schuch, Klaus Brüderle, Daniel Schemmel, Johannes Maass, Wolfgang Meier, Karlheinz Compensating Inhomogeneities of Neuromorphic VLSI Devices Via Short-Term Synaptic Plasticity |
title | Compensating Inhomogeneities of Neuromorphic VLSI Devices Via Short-Term Synaptic Plasticity |
title_full | Compensating Inhomogeneities of Neuromorphic VLSI Devices Via Short-Term Synaptic Plasticity |
title_fullStr | Compensating Inhomogeneities of Neuromorphic VLSI Devices Via Short-Term Synaptic Plasticity |
title_full_unstemmed | Compensating Inhomogeneities of Neuromorphic VLSI Devices Via Short-Term Synaptic Plasticity |
title_short | Compensating Inhomogeneities of Neuromorphic VLSI Devices Via Short-Term Synaptic Plasticity |
title_sort | compensating inhomogeneities of neuromorphic vlsi devices via short-term synaptic plasticity |
topic | Neuroscience |
url | https://www.ncbi.nlm.nih.gov/pmc/articles/PMC2965017/ https://www.ncbi.nlm.nih.gov/pubmed/21031027 http://dx.doi.org/10.3389/fncom.2010.00129 |
work_keys_str_mv | AT billjohannes compensatinginhomogeneitiesofneuromorphicvlsidevicesviashorttermsynapticplasticity AT schuchklaus compensatinginhomogeneitiesofneuromorphicvlsidevicesviashorttermsynapticplasticity AT bruderledaniel compensatinginhomogeneitiesofneuromorphicvlsidevicesviashorttermsynapticplasticity AT schemmeljohannes compensatinginhomogeneitiesofneuromorphicvlsidevicesviashorttermsynapticplasticity AT maasswolfgang compensatinginhomogeneitiesofneuromorphicvlsidevicesviashorttermsynapticplasticity AT meierkarlheinz compensatinginhomogeneitiesofneuromorphicvlsidevicesviashorttermsynapticplasticity |