LR-CNN: Lightweight Row-centric Convolutional Neural Network Training for Memory Reduction

In the last decade, Convolutional Neural Network with a multi-layer architecture has advanced rapidly. However, training its complex network is very space-consuming, since a lot of intermediate data are preserved across layers, especially when processing high-dimension inputs with a big batch size....

Ausführliche Beschreibung

Bibliographische Detailangaben

Veröffentlicht in:	arXiv.org 2024-01
Hauptverfasser:	Wang, Zhigang, Yang, Hangyu, Wang, Ning, Xu, Chuanfei, Nie, Jie, Wei, Zhiqiang, Gu, Yu, Yu, Ge
Format:	Artikel
Sprache:	eng
Schlagworte:	Artificial neural networks Cost analysis Lightweight Multilayers Neural networks Reduction Training
Online-Zugang:	Volltext
Tags:	Tag hinzufügen Keine Tags, Fügen Sie den ersten Tag hinzu!