Combining SNNs with Filtering for Efficient Neural Decoding in Implantable Brain-Machine Interfaces

TL;DR

This paper demonstrates that combining signal filtering with Spiking Neural Networks significantly enhances neural decoding performance in implantable brain-machine interfaces, approaching the accuracy of LSTM networks with minimal additional cost.

Contribution

It introduces a novel approach of integrating traditional filtering techniques with SNNs to improve decoding accuracy in resource-constrained neural interfaces.

Findings

Bessel filters improve SNN decoding performance.

Significant $5\\%$ to $8\\\%$ gains in $R^2$ metric.

State-of-the-art results achieved for the dataset.

Abstract

While it is important to make implantable brain-machine interfaces (iBMI) wireless to increase patient comfort and safety, the trend of increased channel count in recent neural probes poses a challenge due to the concomitant increase in the data rate. Extracting information from raw data at the source by using edge computing is a promising solution to this problem, with integrated intention decoders providing the best compression ratio. Recent benchmarking efforts have shown recurrent neural networks to be the best solution. Spiking Neural Networks (SNN) emerge as a promising solution for resource efficient neural decoding while Long Short Term Memory (LSTM) networks achieve the best accuracy. In this work, we show that combining traditional signal processing techniques, namely signal filtering, with SNNs improve their decoding performance significantly for regression tasks, closing the gap with LSTMs, at little added cost. Results with different filters are shown with Bessel filters providing best performance. Two block-bidirectional Bessel filters have been used--one for low latency and another for high accuracy. Adding the high accuracy variant of the Bessel filters to the output of ANN, SNN and variants provided statistically significant benefits with maximum gains of $\approx 5\%$ and $8\%$ in $R^2$ for two SNN topologies (SNN\_Streaming and SNN\_3D). Our work presents state of the art results for this dataset and paves the way for decoder-integrated-implants of the future.