Convergence of a modified gradient-based learning algorithm with penalty for single-hidden-layer feed-forward networks.
Jian WangBingjie ZhangZhaoyang SangYusong LiuShujun WuQuan MiaoPublished in: Neural Comput. Appl. (2020)
Keyphrases
- single hidden layer
- learning algorithm
- neural network
- feedforward neural networks
- extreme learning machine
- activation function
- hidden layer
- back propagation
- feed forward neural networks
- learning rate
- error function
- artificial neural networks
- convergence rate
- convergence speed
- feed forward
- support vector regression
- learning speed
- recurrent neural networks
- hidden nodes
- hidden neurons
- learning tasks
- training data
- genetic algorithm
- training algorithm
- rbf network
- machine learning algorithms
- active learning
- objective function
- multi layer
- latent variables
- basis functions
- data fusion
- maximum likelihood
- machine learning