Porting Deep Spiking Q-Networks to neuromorphic chip Loihi

Mahmoud Akl, Yulia Sandamirskaya, Florian Walter, Alois Knoll

Publikation: Beitrag in Buch/Bericht/KonferenzbandKonferenzbeitragBegutachtung

3 Zitate (Scopus)

Abstract

Deep neural networks (DNNs) set the benchmark in many tasks in perception and control. Spiking versions of DNNs, implemented on neuromorphic hardware can enable orders of magnitude lower power consumption and low latency during network use. In this paper, we explore behavior and generalization capability of spiking, quantized spiking, and hardware implementation of deep Q-networks in two classical reinforcement learning tasks. We found that spiking neural networks have slightly decreased performance compared to non-spiking network, but we can avoid performance degradation from quantization and in-chip implementation. We conclude that since hardware implementation leads to lower power consumption and low latency, neuromorphic approach is a promising avenue for deep Q-learning. Furthermore, online learning, enabled in neuromorphic chips, can be used to compensate for the performance decrease in environments with parameter variations.

OriginalspracheEnglisch
TitelICONS 2021 - Proceedings of International Conference on Neuromorphic Systems 2021
Herausgeber (Verlag)Association for Computing Machinery
ISBN (elektronisch)9781450386913
DOIs
PublikationsstatusVeröffentlicht - 27 Juli 2021
Veranstaltung2021 International Conference on Neuromorphic Systems, ICONS 2021 - Virtual, Onlie, USA/Vereinigte Staaten
Dauer: 27 Juli 202129 Juli 2021

Publikationsreihe

NameACM International Conference Proceeding Series

Konferenz

Konferenz2021 International Conference on Neuromorphic Systems, ICONS 2021
Land/GebietUSA/Vereinigte Staaten
OrtVirtual, Onlie
Zeitraum27/07/2129/07/21

Fingerprint

Untersuchen Sie die Forschungsthemen von „Porting Deep Spiking Q-Networks to neuromorphic chip Loihi“. Zusammen bilden sie einen einzigartigen Fingerprint.

Dieses zitieren