Towards a constructive multilayer perceptron for regression task using non-parametric clustering. A case study of Photo-Z redshift reconstruction.
Cyrine ArouriEngelbert Mephu NguifoSabeur AridhiCécile RoucelleGaëlle Bonnet-LoosliNorbert TsopzéPublished in: CoRR (2014)
Keyphrases
- multilayer perceptron
- neural network
- radial basis function network
- artificial neural networks
- radial basis function
- back propagation
- probabilistic neural networks
- hidden layer
- regression model
- neural network model
- input vector
- activation function
- commonly applied
- radial basis function neural network
- neuro fuzzy models
- image reconstruction
- input vectors
- case study
- modular neural network
- data sets
- rbf neural network
- rbf network
- gaussian processes
- linear regression
- support vector
- backpropagation algorithm
- support vector regression
- similarity measure
- decision making