An experimental comparison of the Bayesian Ying-Yang criteria and cross validation for selection on number of hidden units in feedforward networks.
Wing-Kai LamLei XuPublished in: ICASSP (1998)
Keyphrases
- cross validation
- feed forward
- number of hidden units
- hidden layer
- neural network
- model selection
- back propagation
- neural nets
- activation function
- feed forward neural networks
- artificial neural networks
- recurrent neural networks
- support vector
- training set
- hyperparameters
- training algorithm
- radial basis function
- decision making
- bayesian networks
- learning algorithm
- multi layer
- training data
- artificial intelligence
- high dimensional