TJU-DNN: A trajectory-unified framework for training deep neural networks and its applications.
Xian-Long LvHsiao-Dong ChiangBin WangYong-Feng ZhangPublished in: Neurocomputing (2023)
Keyphrases
- training process
- unified framework
- neural network
- training algorithm
- feed forward neural networks
- neural network training
- feedforward neural networks
- training data
- pattern recognition
- backpropagation algorithm
- deep architectures
- neural network structure
- multi layer perceptron
- artificial neural networks
- back propagation
- trajectory data
- deep learning
- training patterns
- error back propagation
- multilayer neural network
- network architecture
- recurrent neural networks
- fuzzy logic
- training set
- e learning
- genetic algorithm
- radial basis function network
- multi layer
- computer software
- feed forward
- recurrent networks
- self organizing maps
- supervised learning