Daniel@0: Daniel@0:
Daniel@0:Daniel@0: g = mlpderiv(net, x)Daniel@0: Daniel@0: Daniel@0:
g = mlpderiv(net, x)
takes a network data structure net
Daniel@0: and a matrix of input vectors x
and returns a three-index matrix
Daniel@0: g
whose i
, j
, k
element contains the
Daniel@0: derivative of network output k
with respect to weight or bias
Daniel@0: parameter j
for input pattern i
. The ordering of the
Daniel@0: weight and bias parameters is defined by mlpunpak
.
Daniel@0:
Daniel@0: mlp
, mlppak
, mlpgrad
, mlpbkp
Copyright (c) Ian T Nabney (1996-9) Daniel@0: Daniel@0: Daniel@0: Daniel@0: