Methodology based on spiking neural networks for univariate time-series forecasting

Spiking Neural Networks (SNN) are recognised as well-suited for processing spatiotemporal information with ultra-low energy consumption. However, proposals based on SNN for classification tasks are more common than for forecasting problems. In this sense, this paper presents a new general training m...

Ausführliche Beschreibung

Bibliographische Detailangaben

Veröffentlicht in:	Neural networks Jg. 173; S. 106171
Hauptverfasser:	Lucas, Sergio, Portillo, Eva
Format:	Journal Article
Sprache:	Englisch
Veröffentlicht:	United States Elsevier Ltd 01.05.2024
Schlagworte:	Forecasting PWM based encoding–decoding algorithm Spiking Neural Network Supervised learning Surrogate gradient PWM based encoding–decoding algorithm Surrogate gradient Spiking Neural Network Supervised learning Forecasting
ISSN:	0893-6080, 1879-2782, 1879-2782
Online-Zugang:	Volltext
Tags:	Tag hinzufügen Keine Tags, Fügen Sie den ersten Tag hinzu!