Joint Optimization of Quantization and Structured Sparsity for Compressed Deep Neural Networks

Joint Optimization of Quantization and Structured Sparsity for Compressed Deep Neural Networks

abstract: Deep neural networks (DNN) have shown tremendous success in various cognitive tasks, such as image classification, speech recognition, etc. However, their usage on resource-constrained edge devices has been limited due to high computation and large memory requirement. To overcome these c...

Full description

Bibliographic Details
Other Authors: Srivastava, Gaurav (Author)
Format: Dissertation
Language:English
Published: 2018
Subjects:
Artificial intelligence
Computer engineering
Computer science
Deep learning
Deep Neural Networks
DNN quantization
DNN structured sparsity
DNN weight memory
Pareto-optimal
Online Access:http://hdl.handle.net/2286/R.I.50451

Internet

http://hdl.handle.net/2286/R.I.50451

Similar Items