OPQ: Compressing Deep Neural Networks with One-shot Pruning-Quantization.
Peng HuXi PengHongyuan ZhuMohamed M. Sabry AlyJie LinPublished in: CoRR (2022)
Keyphrases
- neural network
- fuzzy logic
- artificial neural networks
- neural nets
- quantization error
- pattern recognition
- back propagation
- pruning method
- genetic algorithm
- structured light
- multi layer
- data compression
- search space
- multilayer perceptron
- feed forward
- neural network model
- cellular neural networks
- pruning methods
- adaptive resonance theory
- neural network is trained
- rule extraction
- multi layer perceptron
- associative memory
- recurrent neural networks
- self organizing maps
- reinforcement learning
- image processing