An Energy-Efficient Spiking Neural Network for Finger Velocity Decoding for Implantable Brain-Machine Interface

TL;DR

This paper introduces a novel energy-efficient spiking neural network decoder for implantable brain-machine interfaces that matches state-of-the-art accuracy while significantly reducing computational and memory requirements.

Contribution

The paper presents a new SNN decoder trained with enhanced spatio-temporal backpropagation, optimized for low-power implantable BMI systems, with comparable accuracy to traditional ANNs.

Findings

Achieves similar correlation coefficient as state-of-the-art ANN decoders.

Requires only 6.8% of the computation operations of ANNs.

Uses only 9.4% of the memory access compared to ANNs.

Abstract

Brain-machine interfaces (BMIs) are promising for motor rehabilitation and mobility augmentation. High-accuracy and low-power algorithms are required to achieve implantable BMI systems. In this paper, we propose a novel spiking neural network (SNN) decoder for implantable BMI regression tasks. The SNN is trained with enhanced spatio-temporal backpropagation to fully leverage its ability in handling temporal problems. The proposed SNN decoder achieves the same level of correlation coefficient as the state-of-the-art ANN decoder in offline finger velocity decoding tasks, while it requires only 6.8% of the computation operations and 9.4% of the memory access.