Synaptic Tunnel Field-Effect Transistors for Extremely-Low-Power Operation

Synaptic Tunnel Field-Effect Transistors for Extremely-Low-Power Operation

A synaptic cell composed of two tunnel field-effect transistors (TFETs) which is capable of XNOR operation for binary neural networks has been experimentally demonstrated. Our proposed synaptic TFETs feature lower current during inference and higher programming efficiency during weight transfer than...

Ausführliche Beschreibung

Gespeichert in:
Bibliographische Detailangaben
Veröffentlicht in:IEEE electron device letters 2022-07, Vol.43 (7), p.1149-1152
Hauptverfasser: Lee, Jang Woo, Woo, Jae Seung, Choi, Woo Young
Format: Artikel
Sprache:eng
Schlagworte:
Binary neural network
Bit error rate
Computer architecture
Electric fields
extremely-low-power operation
Field effect transistors
MOSFET
Neural networks
neuromorphic computing
Programming
Semiconductor devices
Synapses
synaptic tunnel field-effect transistor
TFETs
Transistors
Tunnels
Online-Zugang:Volltext bestellen
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
Beschreibung
Zusammenfassung:A synaptic cell composed of two tunnel field-effect transistors (TFETs) which is capable of XNOR operation for binary neural networks has been experimentally demonstrated. Our proposed synaptic TFETs feature lower current during inference and higher programming efficiency during weight transfer than conventional synaptic transistors. Moreover, the fabricated synaptic TFET arrays satisfy the neurobiological energy requirement (\!\sim 10 fJ per synaptic event) and low bit-error rate of 6.7\times10 −7 %.
ISSN:0741-3106
1558-0563
DOI:10.1109/LED.2022.3179173