Journal
INFORMATICS-BASEL
Volume 8, Issue 4, Pages -Publisher
MDPI
DOI: 10.3390/informatics8040077
Keywords
deep learning; neural networks pruning; model compression
Funding
- Deanship of Scientific Research, King Khalid University of Kingdom of Saudi Arabia [RGP1/207/42]
Ask authors/readers for more resources
This paper provides an overview of popular methods for compressing and accelerating deep neural networks, including pruning, quantization, and low-rank factorization. The focus is on reducing redundancy in model parameters while maintaining performance advantages.
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.
Authors
I am an author on this paper
Click your name to claim this paper and add it to your profile.
Reviews
Recommended
No Data Available