An In-Memory-Computing Charge-Domain Ternary CNN Classifier

The article presents a charge-domain computing ternary neural network (TNN) classifier with a complete four-layer neural network (NN) on a chip. The proposed ternary network provides 1.5-b resolution (0/ + 1/ - 1) for weights and activations, leading to 3.9 \times fewer operations (OPs) per inferen...

Ausführliche Beschreibung

Gespeichert in:

Bibliographische Detailangaben
Veröffentlicht in:	IEEE journal of solid-state circuits 2023-05, Vol.58 (5), p.1-12
Hauptverfasser:	Yang, Xiangxing, Zhu, Keren, Tang, Xiyuan, Wang, Meizhi, Zhan, Mingtao, Lu, Nanshu, Kulkarni, Jaydeep P., Pan, David Z., Liu, Yongpan, Sun, Nan
Format:	Artikel
Sprache:	eng
Schlagworte:	Accuracy Artificial neural networks Capacitors Classification Classifiers Computation Computer architecture Digital to analog converters Domains In-memory computing mixed-signal processing Neural networks Neurons Registers switched capacitors (SCs) Switches Switching Synapses ternary neural networks (TNNs) Voltage
Online-Zugang:	Volltext bestellen
Tags:	Tag hinzufügen Keine Tags, Fügen Sie den ersten Tag hinzu!

Schreiben Sie den ersten Kommentar!