PhD Forum Abstract: Understanding Deep Model Compression for IoT Devices

Rahim Entezari, Olga Saukh

Research output: Chapter in Book/Report/Conference proceedingConference paperpeer-review

Abstract

Today's deep neural networks require substantial computation resources for their training, storage, and inference, which limits their effective use on resource-constrained devices. Many recent research activities explore different options for compressing and optimizing deep models for the Internet of Things (IoT). Our work so far has focused on two important aspects of deep neural network compression: class-dependent model compression and explainable compression. We shortly summarize our contributions and conclude with an outline of our future research directions.
Original languageEnglish
Title of host publicationProceedings - 2020 19th ACM/IEEE International Conference on Information Processing in Sensor Networks, IPSN 2020
Pages385-386
Number of pages2
ISBN (Electronic)978-1-7281-5497-8
DOIs
Publication statusPublished - 21 Apr 2020
Event19th ACM/IEEE International Conference on Information Processing in Sensor Networks: IPSN 2020 - Virtuell, Sydney, Australia
Duration: 21 Apr 202024 Apr 2020
Conference number: 19
https://ipsn.acm.org/2020/

Publication series

NameProceedings - 2020 19th ACM/IEEE International Conference on Information Processing in Sensor Networks, IPSN 2020

Conference

Conference19th ACM/IEEE International Conference on Information Processing in Sensor Networks
Abbreviated titleIPSN 2020
Country/TerritoryAustralia
CitySydney
Period21/04/2024/04/20
Internet address

Keywords

  • deep neural networks
  • Internet of Things
  • model compression

ASJC Scopus subject areas

  • Information Systems and Management
  • Signal Processing
  • Computer Networks and Communications

Fingerprint

Dive into the research topics of 'PhD Forum Abstract: Understanding Deep Model Compression for IoT Devices'. Together they form a unique fingerprint.

Cite this