Back to Search
Start Over
Deep Neural Network Compression Method Based on Product Quantization
- Source :
- Web of Science
- Publication Year :
- 2020
- Publisher :
- IEEE, 2020.
-
Abstract
- In this paper a method based on the combination of product quantization and pruning to compress deep neural network with large size model and great amount of calculation is proposed. First of all, we use pruning to reduce redundant parameters in deep neural network, and then refine the tune network for fine tuning. Then we use product quantization to quantize the parameters of the neural network to 8 bits, which reduces the storage overhead so that the deep neural network can be deployed in embedded devices. For the classification tasks in the Mnist dataset and Cifar10 dataset, the network models such as LeNet5, AlexNet, ResNet are compressed to 23 to 38 times without losing accuracy as much as possible.
- Subjects :
- 0209 industrial biotechnology
Artificial neural network
business.industry
Computer science
Vector quantization
Pattern recognition
02 engineering and technology
Residual neural network
020901 industrial engineering & automation
0202 electrical engineering, electronic engineering, information engineering
Overhead (computing)
020201 artificial intelligence & image processing
Product quantization
Artificial intelligence
Pruning (decision trees)
business
MNIST database
Network model
Subjects
Details
- Database :
- OpenAIRE
- Journal :
- 2020 39th Chinese Control Conference (CCC)
- Accession number :
- edsair.doi.dedup.....5e3650d22ae7104fe8bce01a6b2f6cfe