Neural Recording Power Optimization Through Machine Learning Guided Resolution Reconfiguration

TL;DR

This paper introduces a system-level optimization technique called resolution reconfiguration for neural recording implants, significantly reducing power consumption by adjusting channel resolution based on importance, across various neural decoding applications.

Contribution

The paper presents a novel resolution reconfiguration method guided by machine learning importance metrics, achieving substantial power savings over traditional channel selection methods.

Findings

Resolution reconfiguration saves up to 23x power in neural decoding tasks.

It outperforms channel selection by 1.6x to 5.2x in power savings.

Applicable across seizure detection, gesture recognition, and force regression.

Abstract

Neural recording implants are a crucial tool for both neuroscience research and enabling new clinical applications. The power consumption of high channel count implants is dominated by the circuits used to amplify and digitize neural signals. Since circuit designers have pushed the efficiency of these circuits close to the theoretical physical limits, reducing power further requires system level optimization. Recent advances use a strategy called channel selection, in which less important channels are turned off to save power. We demonstrate resolution reconfiguration, in which the resolution of less important channels is scaled down to save power. Our approach leverages variable importance of each channel inside machine-learning-based decoders and we trial this methodology across three applications: seizure detection, gesture recognition, and force regression. With linear decoders, resolution reconfiguration saves 8.7x, 12.8x, and 23.0x power compared to a traditional recording array for each task respectively. It further saves 1.6x, 3.4x, and 5.2x power compared to channel selection. The results demonstrate the power benefits of resolution reconfigurable front-ends and their wide applicability to neural decoding problems.