What Happens on the Edge, Stays on the Edge: Toward Compressive Deep Learning

TL;DR

This paper introduces a hybrid hardware-software framework that compresses data during acquisition and uses tailored deep networks to enable efficient machine learning on resource-constrained edge devices.

Contribution

It proposes a novel compressive sensing-inspired approach combined with specialized deep networks for efficient edge machine learning.

Findings

Reduces computational complexity and memory requirements.

Demonstrates effectiveness through numerical simulations.

Compatible with existing on-device techniques.

Abstract

Machine learning at the edge offers great benefits such as increased privacy and security, low latency, and more autonomy. However, a major challenge is that many devices, in particular edge devices, have very limited memory, weak processors, and scarce energy supply. We propose a hybrid hardware-software framework that has the potential to significantly reduce the computational complexity and memory requirements of on-device machine learning. In the first step, inspired by compressive sensing, data is collected in compressed form simultaneously with the sensing process. Thus this compression happens already at the hardware level during data acquisition. But unlike in compressive sensing, this compression is achieved via a projection operator that is specifically tailored to the desired machine learning task. The second step consists of a specially designed and trained deep network. As concrete example we consider the task of image classification, although the proposed framework is more widely applicable. An additional benefit of our approach is that it can be easily combined with existing on-device techniques. Numerical simulations illustrate the viability of our method.