Navigation überspringen
Universitätsbibliothek Heidelberg
Standort: ---
Exemplare: ---
heiBIB
 Online-Ressource
Verfasst von:Stradmann, Yannik [VerfasserIn]   i
 Billaudelle, Sebastian [VerfasserIn]   i
 Breitwieser, Oliver [VerfasserIn]   i
 Ebert, Falk [VerfasserIn]   i
 Emmel, Arne [VerfasserIn]   i
 Husmann, Dan [VerfasserIn]   i
 Ilmberger, Joscha [VerfasserIn]   i
 Müller, Eric [VerfasserIn]   i
 Spilger, Philipp [VerfasserIn]   i
 Weis, Johannes [VerfasserIn]   i
 Schemmel, Johannes [VerfasserIn]   i
Titel:Demonstrating analog inference on the BrainScaleS-2 mobile system
Verf.angabe:Yannik Stradmann, Sebastian Billaudelle, Oliver Breitwieser, Falk Leonard Ebert, Arne Emmel, Dan Husmann, Joscha Ilmberger, Eric Müller, Philipp Spilger, Johannes Weis, and Johannes Schemmel (Member, IEEE)
E-Jahr:2022
Jahr:21 September 2022
Umfang:11 S.
Fussnoten:"Date of current version 24 October 2022" ; Gesehen am 29.09.2022
Titel Quelle:Enthalten in: IEEE open journal of circuits and systems
Ort Quelle:New York, NY : IEEE, 2020
Jahr Quelle:2022
Band/Heft Quelle:3(2022), Seite 252-262
ISSN Quelle:2644-1225
Abstract:We present the BrainScaleS-2 mobile system as a compact analog inference engine based on the BrainScaleS-2 ASIC and demonstrate its capabilities at classifying a medical electrocardiogram dataset. The analog network core of the ASIC is utilized to perform the multiply-accumulate operations of a convolutional deep neural network. At a system power consumption of 5.6W, we measure a total energy consumption of 192 μJ for the ASIC and achieve a classification time of 276 μs per electrocardiographic patient sample. Patients with atrial fibrillation are correctly identified with a detection rate of (93.7 ± 0.7)% at (14.0 ± 1.0)% false positives. The system is directly applicable to edge inference applications due to its small size, power envelope, and flexible I/O capabilities. It has enabled the BrainScaleS-2 ASIC to be operated reliably outside a specialized lab setting. In future applications, the system allows for a combination of conventional machine learning layers with online learning in spiking neural networks on a single neuromorphic platform.
DOI:doi:10.1109/OJCAS.2022.3208413
URL:kostenfrei: Volltext: https://doi.org/10.1109/OJCAS.2022.3208413
 kostenfrei: Volltext: https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=9896927
 DOI: https://doi.org/10.1109/OJCAS.2022.3208413
Datenträger:Online-Ressource
Sprache:eng
Sach-SW:accelerator
 analog computing
 Central Processing Unit
 convolutional deep neural networks
 electrocardiography
 Field programmable gate arrays
 inference
 low-power
 medical
 neuromorphic
 Neuromorphics
 Neurons
 Random access memory
 Synapses
 Virtual machine monitors
K10plus-PPN:1817798316
Verknüpfungen:→ Zeitschrift
 
 
Lokale URL UB: Zum Volltext

Permanenter Link auf diesen Titel (bookmarkfähig):  https://katalog.ub.uni-heidelberg.de/titel/68969393   QR-Code
zum Seitenanfang