reviewApplied IntelligenceSep 2, 2024HYBRID OA

A comprehensive review of model compression techniques in machine learning

Universidade Federal do Amazonas · University of Manchester

Indexed incrossref

Abstract

Abstract This paper critically examines model compression techniques within the machine learning (ML) domain, emphasizing their role in enhancing model efficiency for deployment in resource-constrained environments, such as mobile devices, edge computing, and Internet of Things (IoT) systems. By systematically exploring compression techniques and lightweight design architectures, it is provided a comprehensive understanding of their operational contexts and effectiveness. The synthesis of these strategies reveals a dynamic interplay between model performance and computational demand, highlighting the balance required for optimal application. As machine learning (ML) models grow increasingly complex and…

Citation impact

181
total citations
FWCI
56.81
Percentile
100%
References
291
Citations per year

Authors

4

Topics & keywords

Keywords
  • Computer science
  • Software deployment
  • Artificial intelligence
  • Field (mathematics)
  • Resource efficiency
  • Distributed computing
  • Machine learning
  • Software engineering
No related works found for this paper.

Funding