Value-aware Quantization for Training and Inference of Neural Networks.
Eunhyeok ParkSungjoo YooPeter VajdaPublished in: CoRR (2018)
Keyphrases
- neural network
- training process
- training algorithm
- feed forward neural networks
- multi layer perceptron
- feedforward neural networks
- backpropagation algorithm
- back propagation
- pattern recognition
- training patterns
- fuzzy logic
- structured prediction
- neural network training
- radial basis function network
- multilayer perceptron
- error back propagation
- probabilistic inference
- training set
- data sets
- neural network structure
- multilayer neural network
- supervised learning
- artificial neural networks
- training phase
- activation function
- multi layer
- belief networks
- competitive learning
- self organizing maps
- fault diagnosis
- inference process
- test set
- training examples
- multiresolution
- genetic algorithm