Training high-performance and large-scale deep neural networks with full 8-bit integers.
Yukuan YangLei DengShuang WuTianyi YanYuan XieGuoqi LiPublished in: Neural Networks (2020)
Keyphrases
- neural network
- training process
- training algorithm
- feed forward neural networks
- error back propagation
- feedforward neural networks
- back propagation
- deep architectures
- multi layer perceptron
- real life
- pattern recognition
- data intensive
- training examples
- test set
- recurrent neural networks
- real world
- neural network structure
- neural network training
- recurrent networks
- data sets
- small scale
- genetic algorithm
- network architecture
- training phase
- high efficiency
- feed forward
- sufficient conditions
- scientific computing
- training patterns
- online learning
- backpropagation algorithm
- fuzzy logic
- training set
- real time
- multilayer neural network