Explicit Loss-Error-Aware Quantization for Low-Bit Deep Neural Networks.
Aojun ZhouAnbang YaoKuan WangYurong ChenPublished in: CVPR (2018)
Keyphrases
- neural network
- quantization error
- uniform quantization
- error propagation
- genetic algorithm
- pattern recognition
- error rate
- back propagation
- artificial neural networks
- fuzzy logic
- quantization scheme
- multilayer perceptron
- general loss functions
- feedforward neural networks
- recurrent neural networks
- neural network model
- error bounds
- prediction error
- compression scheme
- adaptive quantization
- successive approximation
- fault diagnosis