Buchumschlag

Six networks on a universal neuromorphic computing substrate

In this study, we present a highly configurable neuromorphic computing substrate and use it for emulating several types of neural networks. At the heart of this system lies a mixed-signal chip, with analog implementations of neurons and synapses and digital transmission of action potentials. Major a...

Ausführliche Beschreibung

Gespeichert in:
Bibliographische Detailangaben
Hauptverfasser: Pfeil, Thomas (VerfasserIn) , Grübl, Andreas (VerfasserIn) , Jeltsch, Sebastian (VerfasserIn) , Müller, Eric (VerfasserIn) , Müller, Paul (VerfasserIn) , Petrovici, Mihai A. (VerfasserIn) , Schmuker, Michael (VerfasserIn) , Brüderle, Daniel (VerfasserIn) , Schemmel, Johannes (VerfasserIn) , Meier, Karlheinz (VerfasserIn)
Dokumenttyp: Article (Journal)
Sprache:Englisch
Veröffentlicht: 18 February 2013
In: Frontiers in neuroscience
Year: 2013, Jahrgang: 7, Pages: 1-17
ISSN:1662-453X
DOI:10.3389/fnins.2013.00011
Online-Zugang:Resolving-System, kostenfrei, Volltext: https://doi.org/10.3389/fnins.2013.00011
Verlag, kostenfrei, Volltext: https://www.frontiersin.org/article/10.3389/fnins.2013.00011
Volltext
Verfasserangaben:Thomas Pfeil, Andreas Grübl, Sebastian Jeltsch, Eric Müller, Paul Müller, Mihai A. Petrovici, Michael Schmuker, Daniel Brüderle, Johannes Schemmel and Karlheinz Meier
Beschreibung
Zusammenfassung:In this study, we present a highly configurable neuromorphic computing substrate and use it for emulating several types of neural networks. At the heart of this system lies a mixed-signal chip, with analog implementations of neurons and synapses and digital transmission of action potentials. Major advantages of this emulation device, which has been explicitly designed as a universal neural network emulator, are its inherent parallelism and high acceleration factor compared to conventional computers. Its configurability allows the realization of almost arbitrary network topologies and the use of widely varied neuronal and synaptic parameters. Fixed-pattern noise inherent to analog circuitry is reduced by calibration routines. An integrated development environment allows neuroscientists to operate the device without any prior knowledge of neuromorphic circuit design. As a showcase for the capabilities of the system, we describe the successful emulation of six different neural networks which cover a broad spectrum of both structure and functionality.
Beschreibung:Gesehen am 20.01.2022
Beschreibung:Online Resource
ISSN:1662-453X
DOI:10.3389/fnins.2013.00011

Ähnliche Einträge