Hierarchical Threshold Pruning Based on Uniform Response Criterion

Convolutional neural networks (CNNs) have been successfully applied to various fields. However, CNNs' overparameterization requires more memory and training time, making it unsuitable for some resource-constrained devices. To address this issue, filter pruning as one of the most efficient ways...

Ausführliche Beschreibung

Bibliographische Detailangaben

Veröffentlicht in:	IEEE transaction on neural networks and learning systems 2024-08, Vol.35 (8), p.10869-10881
Hauptverfasser:	Qian, Yaguan, He, Zhiqiang, Wang, Yuqi, Wang, Bin, Ling, Xiang, Gu, Zhaoquan, Wang, Haijiang, Zeng, Shaoning, Swaileh, Wassim
Format:	Artikel
Sprache:	eng
Schlagworte:	Convolutional neural networks Electronic mail Filter pruning hierarchical threshold pruning (HTP) Information filters model compression Redundancy Software Task analysis Training uniform response criterion (URC)
Online-Zugang:	Volltext bestellen
Tags:	Tag hinzufügen Keine Tags, Fügen Sie den ersten Tag hinzu!