Research on Deep Neural Network Model Compression Based on Quantification Pruning and Huffmann Encoding.
Cong WeiZhiyong LuZhiyong LinChong ZhongPublished in: ICIC (2) (2021)
Keyphrases
- neural network model
- neural network
- arithmetic coding
- efficient compression
- artificial neural networks
- run length encoding
- compression scheme
- data compression
- input variables
- network architecture
- search space
- image compression
- complexity reduction
- compression ratio
- bp neural network
- using artificial neural networks
- rbf neural network
- compression algorithm
- neural models
- fractal image compression
- back propagation neural network
- multi layer perceptron
- multilayer perceptron
- block coding
- pruning method
- back propagation
- dynamic characteristics
- lossless compression
- hopfield network
- wavelet transformed
- bit rate
- compressed data
- vector quantization