Lightweight Deep Learning for Resource-Constrained Environments: A Survey

TL;DR

This survey reviews methods for designing, compressing, and accelerating deep learning models suitable for resource-limited devices like mobile phones and microcontrollers, highlighting future directions in TinyML and large language models.

Contribution

It provides comprehensive guidance on lightweight model design, compression, and hardware acceleration, and discusses future deployment challenges for TinyML and large language models.

Findings

Guidance on designing lightweight deep learning models.

Analysis of compression and hardware acceleration techniques.

Identification of future challenges in deploying TinyML and large language models.

Abstract

Over the past decade, the dominance of deep learning has prevailed across various domains of artificial intelligence, including natural language processing, computer vision, and biomedical signal processing. While there have been remarkable improvements in model accuracy, deploying these models on lightweight devices, such as mobile phones and microcontrollers, is constrained by limited resources. In this survey, we provide comprehensive design guidance tailored for these devices, detailing the meticulous design of lightweight models, compression methods, and hardware acceleration strategies. The principal goal of this work is to explore methods and concepts for getting around hardware constraints without compromising the model's accuracy. Additionally, we explore two notable paths for lightweight deep learning in the future: deployment techniques for TinyML and Large Language Models. Although these paths undoubtedly have potential, they also present significant challenges, encouraging research into unexplored areas.