Picture for Xing Sheng

Xing Sheng

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

Add code
Jan 07, 2024
Chao Zhang, Yongxiang Guo, Dawid Sheng, Zhixiong Ma, Chao Sun, Yuwei Zhang, Wenxin Zhao, Fenyan Zhang, Tongfei Wang, Xing Sheng(+1 more)
Figure 1 for A Closed-loop Brain-Machine Interface SoC Featuring a 0.2$μ$J/class Multiplexer Based Neural Network
Figure 2 for A Closed-loop Brain-Machine Interface SoC Featuring a 0.2$μ$J/class Multiplexer Based Neural Network
Figure 3 for A Closed-loop Brain-Machine Interface SoC Featuring a 0.2$μ$J/class Multiplexer Based Neural Network

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$\mu$J/class in sleep staging task.

* 2 pages, 6 figures. Accepted by IEEE Custom Integrated Circuits Conference (CICC) 2024. The codes for the MUXnet (constructing neural networks using multiplexers instead of multipliers) will be open-sourced after the Journal version of this work is accepted 
Viaarxiv icon
Github IconAccess Paper or Ask Questions
Twitter IconFacebook IconLinkedin IconWhatsapp IconMessenger Icon