Work

Low-power Spike-based Wearable Analytics on RRAM Crossbars

Year: 2025

Type: conference-paper

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 2.1× reduction in latency compared to BP, while delivering upto 7.55% higher inference accuracy on human activity recognition (HAR) tasks.

Source: IEEE International Symposium on Circuits and Systems proceedings

DOI: 10.1109/iscas56072.2025.11043716

Authors: Abhiroop Bhattacharjee, Jinquan Shi, Wei-Chen Chen, Xinxin Wang, Priyadarshini Panda

Institutions: Yale University, Stanford University

Language: English

Topic: Advanced Memory and Neural Computing

Subfield: Electrical and Electronic Engineering

Field: Engineering

Domain: Physical Sciences

Open Access status: green

Funders: National Science Foundation, University of Pennsylvania, Pennsylvania State University, Defense Advanced Research Projects Agency

Awards: EFRI BRAID: Scalable-Learning Neuromorphics, G6671297155, Collaborative Research: Visual Cortex on Silicon, Collaborative Research: SHF: Medium: Memory-efficient Algorithm and Hardware Co-Design for Spike-based Edge Computing