A Novel Fusion Pruning Algorithm Based on Information Entropy Stratification and IoT Application
To further reduce the size of the neural network model and enable the network to be deployed on mobile devices, a novel fusion pruning algorithm based on information entropy stratification is proposed in this paper. Firstly, the method finds similar filters and removes redundant parts by Affinity Pr...
Main Authors: | Hu, M. (Author), Li, M. (Author), Peng, S.-L (Author), Tan, J. (Author), Zhao, M. (Author) |
---|---|
Format: | Article |
Language: | English |
Published: |
MDPI
2022
|
Subjects: | |
Online Access: | View Fulltext in Publisher |
Similar Items
-
Ps and Qs: Quantization-Aware Pruning for Efficient Low Latency Neural Network Inference
by: Benjamin Hawks, et al.
Published: (2021-07-01) -
Accelerating Federated Learning for IoT in Big Data Analytics With Pruning, Quantization and Selective Updating
by: Wenyuan Xu, et al.
Published: (2021-01-01) -
Pruning optimization based on deep convolution neural network
by: Ma Zhinan, et al.
Published: (2018-12-01) -
Differential Evolution Based Layer-Wise Weight Pruning for Compressing Deep Neural Networks
by: Tao Wu, et al.
Published: (2021-01-01) -
Coarse-Grained Pruning of Neural Network Models Based on Blocky Sparse Structure
by: Lan Huang, et al.
Published: (2021-08-01)