Upper bound of the expected training error of neural network regression for a Gaussian noise sequence.
Katsuyuki HagiwaraTaichi HayasakaNaohiro TodaShiro UsuiKazuhiro KunoPublished in: Neural Networks (2001)
Keyphrases
- gaussian noise
- upper bound
- generalization error
- training error
- neural network
- hidden layer
- lower bound
- denoising
- image restoration
- noise level
- model selection
- noisy images
- classification error
- back propagation
- signal to noise ratio
- error rate
- worst case
- neural network model
- sample size
- artificial neural networks
- feed forward
- radial basis function
- cross validation
- gradient method
- recurrent neural networks
- neural nets
- image processing
- adaboost algorithm
- boosting algorithms
- training data
- high quality
- support vector
- base classifiers
- bp neural network
- noise reduction
- image denoising