Low-power Spike-based Wearable Analytics on RRAM Crossbars

TL;DR

This paper presents a low-power, spike-based wearable analytics system using RRAM crossbars and introduces an online adaptation method for SNNs with DFA, achieving significant energy, area, and latency improvements over traditional backpropagation.

Contribution

It proposes a novel online adaptation approach for SNNs on RRAM crossbars using DFA, enhancing energy efficiency and performance in wearable analytics.

Findings

DFA reduces energy consumption by up to 64.1%.

DFA achieves 10.1% lower area overhead than BP.

DFA delivers up to 7.55% higher accuracy on HAR tasks.

Abstract

This work introduces a spike-based wearable analytics system utilizing Spiking Neural Networks (SNNs) deployed on an In-memory Computing engine based on RRAM crossbars, which are known for their compactness and energy-efficiency. Given the hardware constraints and noise characteristics of the underlying RRAM crossbars, we propose online adaptation of pre-trained SNNs in real-time using Direct Feedback Alignment (DFA) against traditional backpropagation (BP). Direct Feedback Alignment (DFA) learning, that allows layer-parallel gradient computations, acts as a fast, energy & area-efficient method for online adaptation of SNNs on RRAM crossbars, unleashing better algorithmic performance against those adapted using BP. Through extensive simulations using our in-house hardware evaluation engine called DFA_Sim, we find that DFA achieves upto 64.1% lower energy consumption, 10.1% lower area overhead, and a 2.1x reduction in latency compared to BP, while delivering upto 7.55% higher inference accuracy on human activity recognition (HAR) tasks.