Daniel@0: Daniel@0:
Daniel@0:Daniel@0: g = rbfbkp(net, x, z, n2, deltas)Daniel@0: Daniel@0: Daniel@0:
g = rbfbkp(net, x, z, n2, deltas)
takes a network data structure
Daniel@0: net
together with a matrix x
of input vectors, a matrix
Daniel@0: z
of hidden unit activations, a matrix n2
of the squared
Daniel@0: distances between centres and inputs, and a matrix deltas
of the
Daniel@0: gradient of the error function with respect to the values of the
Daniel@0: output units (i.e. the summed inputs to the output units, before the
Daniel@0: activation function is applied). The return value is the gradient
Daniel@0: g
of the error function with respect to the network
Daniel@0: weights. Each row of x
corresponds to one input vector.
Daniel@0:
Daniel@0: This function is provided so that the common backpropagation algorithm
Daniel@0: can be used by RBF network models to compute
Daniel@0: gradients for the output values (in rbfderiv
) as well as standard error
Daniel@0: functions.
Daniel@0:
Daniel@0:
rbf
, rbfgrad
, rbfderiv
Copyright (c) Ian T Nabney (1996-9) Daniel@0: Daniel@0: Daniel@0: Daniel@0: