Flexible Quantization for Efficient Convolutional Neural Networks

This work focuses on the efficient quantization of convolutional neural networks (CNNs). Specifically, we introduce a method called non-uniform uniform quantization (NUUQ), a novel quantization methodology that combines the benefits of non-uniform quantization, such as high compression levels, with...

Ausführliche Beschreibung

Bibliographische Detailangaben

Veröffentlicht in:	Electronics (Basel) 2024-05, Vol.13 (10), p.1923
Hauptverfasser:	Zacchigna, Federico Giordano, Lew, Sergio, Lutenberg, Ariel
Format:	Artikel
Sprache:	eng
Schlagworte:	Accuracy Algorithms Artificial neural networks Complexity Decoupling Efficiency Embedded systems Energy consumption Equivalence Field programmable gate arrays Flexibility Neural networks Optimization
Online-Zugang:	Volltext
Tags:	Tag hinzufügen Keine Tags, Fügen Sie den ersten Tag hinzu!