Energy-Aware Deep Learning on Resource-Constrained Hardware

TL;DR

This paper reviews energy-aware deep learning methods tailored for resource-constrained devices like IoT and mobile gadgets, focusing on their techniques, efficiencies, limitations, and future research directions.

Contribution

It provides a comprehensive overview of current energy-aware deep learning approaches, highlighting their methodologies, system implications, and gaps for future exploration.

Findings

Summarizes various energy-efficient DL techniques for IoT and mobile devices.

Identifies limitations in current approaches regarding network types and hardware.

Suggests directions for future research in energy-constrained deep learning.

Abstract

The use of deep learning (DL) on Internet of Things (IoT) and mobile devices offers numerous advantages over cloud-based processing. However, such devices face substantial energy constraints to prolong battery-life, or may even operate intermittently via energy-harvesting. Consequently, \textit{energy-aware} approaches for optimizing DL inference and training on such resource-constrained devices have garnered recent interest. We present an overview of such approaches, outlining their methodologies, implications for energy consumption and system-level efficiency, and their limitations in terms of supported network types, hardware platforms, and application scenarios. We hope our review offers a clear synthesis of the evolving energy-aware DL landscape and serves as a foundation for future research in energy-constrained computing.