Real-time Hyper-Dimensional Reconfiguration at the Edge using Hardware Accelerators

TL;DR

This paper introduces HyDRATE, a low-SWaP hardware system enabling real-time, reconfigurable hyperdimensional computing at the edge, combining quantized neural nets and HD accelerators for efficient, noise-robust classification.

Contribution

It presents a novel hardware and algorithmic framework for real-time hyperdimensional reconfiguration at the edge using non-MAC DNNs and HD computing, with a focus on low-power embedded systems.

Findings

Performance increases with hyperdimension count

Reconfiguration achieved via few-shot learning without backpropagation

System demonstrates low latency and power suitable for edge deployment

Abstract

In this paper we present Hyper-Dimensional Reconfigurable Analytics at the Tactical Edge (HyDRATE) using low-SWaP embedded hardware that can perform real-time reconfiguration at the edge leveraging non-MAC (free of floating-point MultiplyACcumulate operations) deep neural nets (DNN) combined with hyperdimensional (HD) computing accelerators. We describe the algorithm, trained quantized model generation, and simulated performance of a feature extractor free of multiply-accumulates feeding a hyperdimensional logic-based classifier. Then we show how performance increases with the number of hyperdimensions. We describe the realized low-SWaP FPGA hardware and embedded software system compared to traditional DNNs and detail the implemented hardware accelerators. We discuss the measured system latency and power, noise robustness due to use of learnable quantization and HD computing, actual versus simulated system performance for a video activity classification task and demonstration of reconfiguration on this same dataset. We show that reconfigurability in the field is achieved by retraining only the feed-forward HD classifier without gradient descent backpropagation (gradient-free), using few-shot learning of new classes at the edge. Initial work performed used LRCN DNN and is currently extended to use Two-stream DNN with improved performance.