Daniel@0: Daniel@0: Daniel@0: Daniel@0: Netlab Reference Manual rbfprior Daniel@0: Daniel@0: Daniel@0: Daniel@0:

rbfprior Daniel@0:

Daniel@0:

Daniel@0: Purpose Daniel@0:

Daniel@0: Create Gaussian prior and output layer mask for RBF. Daniel@0: Daniel@0:

Daniel@0: Synopsis Daniel@0:

Daniel@0:
Daniel@0: [mask, prior] = rbfprior(rbfunc, nin, nhidden, nout, aw2, ab2)
Daniel@0: Daniel@0: Daniel@0:

Daniel@0: Description Daniel@0:

Daniel@0: [mask, prior] = rbfprior(rbfunc, nin, nhidden, nout, aw2, ab2) Daniel@0: generates a vector Daniel@0: mask that selects only the output Daniel@0: layer weights. This is because most uses of RBF networks in a Bayesian Daniel@0: context have fixed basis functions with the output layer as the only Daniel@0: adjustable parameters. In particular, the Neuroscale output error function Daniel@0: is designed to work only with this mask. Daniel@0: Daniel@0:

The return value Daniel@0: prior is a data structure, Daniel@0: with fields prior.alpha and prior.index, which Daniel@0: specifies a Gaussian prior distribution for the network weights in an Daniel@0: RBF network. The parameters aw2 and ab2 are all Daniel@0: scalars and represent the regularization coefficients for two groups Daniel@0: of parameters in the network corresponding to Daniel@0: second-layer weights, and second-layer biases Daniel@0: respectively. Then prior.alpha represents a column vector of Daniel@0: length 2 containing the parameters, and prior.index is a matrix Daniel@0: specifying which weights belong in each group. Each column has one Daniel@0: element for each weight in the matrix, using the standard ordering as Daniel@0: defined in rbfpak, and each element is 1 or 0 according to Daniel@0: whether the weight is a member of the corresponding group or not. Daniel@0: Daniel@0:

Daniel@0: See Also Daniel@0:

Daniel@0: rbf, rbferr, rbfgrad, evidence
Daniel@0: Pages: Daniel@0: Index Daniel@0:
Daniel@0:

Copyright (c) Ian T Nabney (1996-9) Daniel@0: Daniel@0: Daniel@0: Daniel@0: