Natively neuromorphic LMU architecture for encoding-free SNN-based HAR on commercial edge devices

TL;DR

This paper introduces L2MU, a neuromorphic Recurrent Spiking Neural Network architecture based on LMU and LIF neurons, designed for real-time human activity recognition on commercial edge devices without specialized hardware.

Contribution

The paper presents a natively neuromorphic LMU architecture using LIF neurons, enabling encoding-free processing of raw sensor data on standard edge devices for HAR tasks.

Findings

L2MU achieves effective HAR classification on smartwatch data.

The model runs efficiently on multiple commercial edge devices.

Neuromorphic models can operate without dedicated hardware for sensor data processing.

Abstract

Neuromorphic models take inspiration from the human brain by adopting bio-plausible neuron models to build alternatives to traditional Machine Learning (ML) and Deep Learning (DL) solutions. The scarce availability of dedicated hardware able to actualize the emulation of brain-inspired computation, which is otherwise only simulated, yet still hinders the wide adoption of neuromorphic computing for edge devices and embedded systems. With this premise, we adopt the perspective of neuromorphic computing for conventional hardware and we present the L2MU, a natively neuromorphic Legendre Memory Unit (LMU) which entirely relies on Leaky Integrate-and-Fire (LIF) neurons. Specifically, the original recurrent architecture of LMU has been redesigned by modelling every constituent element with neural populations made of LIF or Current-Based (CuBa) LIF neurons. To couple neuromorphic computing and off-the-shelf edge devices, we equipped the L2MU with an input module for the conversion of real values into spikes, which makes it an encoding-free implementation of a Recurrent Spiking Neural Network (RSNN) able to directly work with raw sensor signals on non-dedicated hardware. As a use case to validate our network, we selected the task of Human Activity Recognition (HAR). We benchmarked our L2MU on smartwatch signals from hand-oriented activities, deploying it on three different commercial edge devices in compressed versions too. The reported results remark the possibility of considering neuromorphic models not only in an exclusive relationship with dedicated hardware but also as a suitable choice to work with common sensors and devices.