Signals to Spikes for Neuromorphic Regulated Reservoir Computing and EMG Hand Gesture Recognition

TL;DR

This paper introduces a novel spike encoding optimization for neuromorphic reservoir computing applied to EMG hand gesture recognition, achieving superior accuracy over state-of-the-art neural networks with biologically inspired models.

Contribution

It presents a new spike encoding hyper-parameter optimization method and demonstrates improved performance of a reservoir computing system on EMG datasets.

Findings

Reservoir with activity regulation achieves 89.72% accuracy on Roshambo EMG dataset.

The approach outperforms state-of-the-art spiking neural networks.

Biologically inspired reservoir computing shows high potential for power-efficient EMG gesture recognition.

Abstract

Surface electromyogram (sEMG) signals result from muscle movement and hence they are an ideal candidate for benchmarking event-driven sensing and computing. We propose a simple yet novel approach for optimizing the spike encoding algorithm's hyper-parameters inspired by the readout layer concept in reservoir computing. Using a simple machine learning algorithm after spike encoding, we report performance higher than the state-of-the-art spiking neural networks on two open-source datasets for hand gesture recognition. The spike encoded data is processed through a spiking reservoir with a biologically inspired topology and neuron model. When trained with the unsupervised activity regulation CRITICAL algorithm to operate at the edge of chaos, the reservoir yields better performance than state-of-the-art convolutional neural networks. The reservoir performance with regulated activity was found to be 89.72% for the Roshambo EMG dataset and 70.6% for the EMG subset of sensor fusion dataset. Therefore, the biologically-inspired computing paradigm, which is known for being power efficient, also proves to have a great potential when compared with conventional AI algorithms.