Power efficient Spiking Neural Network Classifier based on memristive crossbar network for spike sorting application

TL;DR

This paper proposes a power-efficient spike sorting module using a memristive crossbar-based spiking neural network, achieving comparable accuracy to digital methods with significantly reduced power consumption for neural signal classification.

Contribution

It introduces a low-power memristive crossbar SNN classifier and a 2-step shared training scheme for on-chip spike sorting, enhancing efficiency in neural signal processing.

Findings

Memristive crossbar SNN reduces power consumption compared to digital implementations.

The training scheme maintains high accuracy despite memristance variations.

The approach is suitable for implantable biomedical systems with strict power constraints.

Abstract

In this paper authors have presented a power efficient scheme for implementing a spike sorting module. Spike sorting is an important application in the field of neural signal acquisition for implantable biomedical systems whose function is to map the Neural-spikes (N-spikes) correctly to the neurons from which it originates. The accurate classification is a pre-requisite for the succeeding systems needed in Brain-Machine-Interfaces (BMIs) to give better performance. The primary design constraint to be satisfied for the spike sorter module is low power with good accuracy. There lies a trade-off in terms of power consumption between the on-chip and off-chip training of the N-spike features. In the former case care has to be taken to make the computational units power efficient whereas in the later the data rate of wireless transmission should be minimized to reduce the power consumption due to the transceivers. In this work a 2-step shared training scheme involving a K-means sorter and a Spiking Neural Network (SNN) is elaborated for on-chip training and classification. Also, a low power SNN classifier scheme using memristive crossbar type architecture is compared with a fully digital implementation. The advantage of the former classifier is that it is power efficient while providing comparable accuracy as that of the digital implementation due to the robustness of the SNN training algorithm which has a good tolerance for variation in memristance.