g = rbfgrad(net, x, t) [g, gdata, gprior] = rbfgrad(net, x, t)
g = rbfgrad(net, x, t)takes a network data structure
nettogether with a matrix
xof input vectors and a matrix
tof target vectors, and evaluates the gradient
gof the error function with respect to the network weights (i.e. including the hidden unit parameters). The error function is sum of squares. Each row of
xcorresponds to one input vector and each row of
tcontains the corresponding target vector. If the output function is
'neuroscale'then the gradient is only computed for the output layer weights and biases.
[g, gdata, gprior] = rbfgrad(net, x, t) also returns separately
the data and prior contributions to the gradient. In the case of
multiple groups in the prior,
gprior is a matrix with a row
for each group and a column for each weight parameter.
Copyright (c) Ian T Nabney (1996-9)