A Fully Analog Deep Neural Network Inference Accelerator with Pipeline Registers Based on Master-Slave Switched Capacitors

A fully analog pipelined deep neural network (DNN) accelerator is proposed, which is constructed by using pipeline registers based on master-slave switched capacitors. The idea of the master-slave switched capacitors is an analog equivalent of the delayed flip-flop (D-FF) which has been used as a di...

Ausführliche Beschreibung

Bibliographische Detailangaben

Veröffentlicht in:	IEICE Transactions on Electronics 2023/09/01, Vol.E106.C(9), pp.477-485
Hauptverfasser:	MEI, Yaxin, OHSAWA, Takashi
Format:	Artikel
Sprache:	eng
Schlagworte:	Artificial neural networks Capacitors Classification Cycle time deep neural network (DNN) Energy consumption in-memory computing master-slave switched capacitors pipeline register
Online-Zugang:	Volltext
Tags:	Tag hinzufügen Keine Tags, Fügen Sie den ersten Tag hinzu!