Gradient distribution-aware INT8 training for neural networks.
Shuai WangYi KangPublished in: Neurocomputing (2023)
Keyphrases
- neural network
- training process
- training algorithm
- feed forward neural networks
- multi layer perceptron
- backpropagation algorithm
- feedforward neural networks
- pattern recognition
- neural network training
- training set
- back propagation
- fuzzy logic
- multi layer
- error back propagation
- fuzzy systems
- feed forward
- data distribution
- training examples
- image gradient
- training and test data
- training patterns
- edge detection
- recurrent neural networks
- training samples
- maximum likelihood
- absolute difference
- supervised learning
- neural network structure
- genetic algorithm