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...
Other Authors: | Srivastava, Gaurav (Author) |
---|---|
Format: | Dissertation |
Language: | English |
Published: |
2018
|
Subjects: | |
Online Access: | http://hdl.handle.net/2286/R.I.50451 |
Similar Items
-
Automated optimization for memory‐efficient high‐performance deep neural network accelerators
by: HyunMi Kim, et al.
Published: (2020-07-01) -
MOSDA: On-Chip Memory Optimized Sparse Deep Neural Network Accelerator With Efficient Index Matching
by: Hongjie Xu, et al.
Published: (2021-01-01) -
Substituting Convolutions for Neural Network Compression
by: Elliot J. Crowley, et al.
Published: (2021-01-01) -
Fast speaker adaptation using extended diagonal linear transformation for deep neural networks
by: Donghyun Kim, et al.
Published: (2018-11-01) -
CoEdge: Exploiting the Edge-Cloud Collaboration for Faster Deep Learning
by: Liangyan Hu, et al.
Published: (2020-01-01)