Improved Linear Convergence of Training CNNs With Generalizability Guarantees: A One-Hidden-Layer Case.
Shuai ZhangMeng WangJinjun XiongSijia LiuPin-Yu ChenPublished in: IEEE Trans. Neural Networks Learn. Syst. (2021)
Keyphrases
- hidden layer
- feedforward neural networks
- feed forward neural networks
- training algorithm
- back propagation
- backpropagation algorithm
- learning rate
- activation function
- output layer
- recurrent neural networks
- neural network
- number of hidden layers
- feed forward
- single hidden layer
- training error
- multilayer perceptron
- artificial neural networks
- radial basis function
- neural network structure
- rbf neural network
- convergence rate
- learning speed
- number of hidden units
- training process
- neural network model
- multi layer
- neural nets
- cellular neural networks
- input output
- evolutionary algorithm
- training set
- bp neural network
- fuzzy clustering
- random variables
- machine learning