A Closed-loop Brain-Machine Interface SoC Featuring a 0.2$μ$J/class Multiplexer Based Neural Network

Fuente: arXiv
Gespeichert in:
Bibliographische Detailangaben
Hauptverfasser: Zhang, Chao, Guo, Yongxiang, Sheng, Dawid, Ma, Zhixiong, Sun, Chao, Zhang, Yuwei, Zhao, Wenxin, Zhang, Fenyan, Wang, Tongfei, Sheng, Xing, Zhang, Milin
Format: Preprint
Veröffentlicht: 2024
Schlagworte:
Online-Zugang:
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
_version_ 1866910289835851776
author Zhang, Chao
Guo, Yongxiang
Sheng, Dawid
Ma, Zhixiong
Sun, Chao
Zhang, Yuwei
Zhao, Wenxin
Zhang, Fenyan
Wang, Tongfei
Sheng, Xing
Zhang, Milin
author_facet Zhang, Chao
Guo, Yongxiang
Sheng, Dawid
Ma, Zhixiong
Sun, Chao
Zhang, Yuwei
Zhao, Wenxin
Zhang, Fenyan
Wang, Tongfei
Sheng, Xing
Zhang, Milin
contents This work presents the first fabricated electrophysiology-optogenetic closed-loop bidirectional brain-machine interface (CL-BBMI) system-on-chip (SoC) with electrical neural signal recording, on-chip sleep staging and optogenetic stimulation. The first multiplexer with static assignment based table lookup solution (MUXnet) for multiplier-free NN processor was proposed. A state-of-the-art average accuracy of 82.4% was achieved with an energy consumption of only 0.2$μ$J/class in sleep staging task.
format Preprint
id arxiv_https___arxiv_org_abs_2401_03396
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle A Closed-loop Brain-Machine Interface SoC Featuring a 0.2$μ$J/class Multiplexer Based Neural Network
Zhang, Chao
Guo, Yongxiang
Sheng, Dawid
Ma, Zhixiong
Sun, Chao
Zhang, Yuwei
Zhao, Wenxin
Zhang, Fenyan
Wang, Tongfei
Sheng, Xing
Zhang, Milin
Signal Processing
This work presents the first fabricated electrophysiology-optogenetic closed-loop bidirectional brain-machine interface (CL-BBMI) system-on-chip (SoC) with electrical neural signal recording, on-chip sleep staging and optogenetic stimulation. The first multiplexer with static assignment based table lookup solution (MUXnet) for multiplier-free NN processor was proposed. A state-of-the-art average accuracy of 82.4% was achieved with an energy consumption of only 0.2$μ$J/class in sleep staging task.
title A Closed-loop Brain-Machine Interface SoC Featuring a 0.2$μ$J/class Multiplexer Based Neural Network
topic Signal Processing
url https://arxiv.org/abs/2401.03396