No Cover Image

Journal article 52 views 9 downloads

Literature Review of Deep Network Compression

Ali Alqahtani, Xianghua Xie Orcid Logo, Mark Jones Orcid Logo

Informatics, Volume: 8, Issue: 4, Start page: 77

Swansea University Authors: Xianghua Xie Orcid Logo, Mark Jones Orcid Logo

  • 58687.VOR.pdf

    PDF | Version of Record

    Copyright: © 2021 by the authors. This article is an open access article distributed under the terms and conditions of the Creative Commons Attribution (CC-BY) Licence.

    Download (232.3KB)

Abstract

Deep networks often possess a vast number of parameters, and their significant redundancy in parameterization has become a widely-recognized property. This presents significant challenges and restricts many deep learning applications, making the focus on reducing the complexity of models while maint...

Full description

Published in: Informatics
ISSN: 2227-9709
Published: MDPI AG 2021
Online Access: Check full text

URI: https://cronfa.swan.ac.uk/Record/cronfa58687
Tags: Add Tag
No Tags, Be the first to tag this record!
Abstract: Deep networks often possess a vast number of parameters, and their significant redundancy in parameterization has become a widely-recognized property. This presents significant challenges and restricts many deep learning applications, making the focus on reducing the complexity of models while maintaining their powerful performance. In this paper, we present an overview of popular methods and review recent works on compressing and accelerating deep neural networks. We consider not only pruning methods but also quantization methods, and low-rank factorization methods. This review also intends to clarify these major concepts, and highlights their characteristics, advantages, and shortcomings.
Keywords: deep learning; neural networks pruning; model compression
College: College of Science
Funders: This work was supported by the Deanship of Scientific Research, King Khalid University of Kingdom of Saudi Arabia under research grant number (RGP1/207/42).
Issue: 4
Start Page: 77