SpikeDyn: A Framework for Energy-Efficient Spiking Neural Networks with Continual and Unsupervised Learning Capabilities in Dynamic Environments

Spiking Neural Networks (SNNs) bear the potential of efficient unsupervised and continual learning capabilities because of their biological plausibility, but their complexity still poses a serious research challenge to enable their energy-efficient design for resource-constrained scenarios (like emb...

Ausführliche Beschreibung

Bibliographische Detailangaben

Veröffentlicht in:	2021 58th ACM/IEEE Design Automation Conference (DAC) S. 1057 - 1062
Hauptverfasser:	Putra, Rachmad Vidya Wicaksana, Shafique, Muhammad
Format:	Tagungsbericht
Sprache:	Englisch
Veröffentlicht:	IEEE 05.12.2021
Schlagworte:	Adaptation models Analytical models complexity continual learning embedded systems Energy consumption Energy efficiency Heuristic algorithms Inference algorithms SNNs Spiking neural networks Training unsupervised learning
Online-Zugang:	Volltext
Tags:	Tag hinzufügen Keine Tags, Fügen Sie den ersten Tag hinzu!