Recurrent neural network from adder’s perspective: Carry-lookahead RNN

The recurrent network architecture is a widely used model in sequence modeling, but its serial dependency hinders the computation parallelization, which makes the operation inefficient. The same problem was encountered in serial adder at the early stage of digital electronics. In this paper, we disc...

Ausführliche Beschreibung

Bibliographische Detailangaben

Veröffentlicht in:	Neural networks Jg. 144; S. 297 - 306
Hauptverfasser:	Jiang, Haowei, Qin, Feiwei, Cao, Jin, Peng, Yong, Shao, Yanli
Format:	Journal Article
Sprache:	Englisch
Veröffentlicht:	Elsevier Ltd 01.12.2021
Schlagworte:	Carry-lookahead Deep learning Parallel computation Sequence modeling Deep learning Sequence modeling Parallel computation Carry-lookahead
ISSN:	0893-6080, 1879-2782, 1879-2782
Online-Zugang:	Volltext
Tags:	Tag hinzufügen Keine Tags, Fügen Sie den ersten Tag hinzu!