Daniel@0: Daniel@0:
Daniel@0:Daniel@0: Daniel@0: g = mlpgrad(net, x, t) Daniel@0:Daniel@0: Daniel@0: Daniel@0:
g = mlpgrad(net, x, t)
takes a network data structure net
Daniel@0: together with a matrix x
of input vectors and a matrix t
Daniel@0: of target vectors, and evaluates the gradient g
of the error
Daniel@0: function with respect to the network weights. The error funcion
Daniel@0: corresponds to the choice of output unit activation function. Each row
Daniel@0: of x
corresponds to one input vector and each row of t
Daniel@0: corresponds to one target vector.
Daniel@0:
Daniel@0: [g, gdata, gprior] = mlpgrad(net, x, t)
also returns separately
Daniel@0: the data and prior contributions to the gradient. In the case of
Daniel@0: multiple groups in the prior, gprior
is a matrix with a row
Daniel@0: for each group and a column for each weight parameter.
Daniel@0:
Daniel@0:
mlp
, mlppak
, mlpunpak
, mlpfwd
, mlperr
, mlpbkp
Copyright (c) Ian T Nabney (1996-9) Daniel@0: Daniel@0: Daniel@0: Daniel@0: