Power-Optimized Field-Programmable Gate Array Implementation of Neural Activation Functions Using Continued Fractions for AI/ML Workloads

The increasing demand for energy-efficient hardware platforms to support artificial intelligence (AI) and machine learning (ML) algorithms in edge computing has driven the adoption of system-on-chip (SoC) architectures. Implementing neural network (NN) activation functions, such as the hyperbolic ta...

Ausführliche Beschreibung

Gespeichert in:

Bibliographische Detailangaben
Veröffentlicht in:	Electronics (Basel) Jg. 13; H. 24; S. 5026
Hauptverfasser:	Hingu, Chanakya, Fu, Xingang, Saliyu, Taofiki, Hu, Rui, Mishan, Ramkrishna
Format:	Journal Article
Sprache:	Englisch
Veröffentlicht:	Basel MDPI AG 01.12.2024
Schlagworte:	Accuracy Algorithms Analysis Approximation Artificial intelligence Cyclones Digital integrated circuits Digital signal processing Digital signal processors Edge computing Efficiency Embedded systems Energy management systems Field programmable gate arrays Floating point arithmetic Hardware Machine learning Neural networks Optimization Polynomials Power consumption Power management Real time Recurrent neural networks Resource utilization Signal processing System on chip
ISSN:	2079-9292, 2079-9292
Online-Zugang:	Volltext
Tags:	Tag hinzufügen Keine Tags, Fügen Sie den ersten Tag hinzu!

Schreiben Sie den ersten Kommentar!