Deep neural network compression : from sufficient to scarce data

Deep neural network compression : from sufficient to scarce data

The success of overparameterized deep neural networks (DNNs) poses a great challenge to deploy computationally expensive models on edge devices. Numerous model compression (pruning, quantization) methods have been proposed to overcome this challenge: Pruning eliminates unimportant parameters, while...

Full description

Bibliographic Details
Main Author: Chen, Shangyu
Other Authors: Sinno Jialin Pan
Format: Thesis-Doctor of Philosophy
Language:English
Published: Nanyang Technological University 2021
Subjects:
Engineering::Computer science and engineering::Computing methodologies::Artificial intelligence
Online Access:https://hdl.handle.net/10356/146245

Internet

https://hdl.handle.net/10356/146245

Similar Items