Daniel@0: Daniel@0:
Daniel@0:Daniel@0: Daniel@0: g = mdngrad(net, x, t) Daniel@0:Daniel@0: Daniel@0: Daniel@0:
g = mdngrad(net, x, t)
takes a mixture density network data
Daniel@0: structure net
, a matrix x
of input vectors and a matrix
Daniel@0: t
of target vectors, and evaluates the gradient g
of the
Daniel@0: error function with respect to the network weights. The error function
Daniel@0: is negative log likelihood of the target data. Each row of x
Daniel@0: corresponds to one input vector and each row of t
corresponds to
Daniel@0: one target vector.
Daniel@0:
Daniel@0: mdn
, mdnfwd
, mdnerr
, mdnprob
, mlpbkp
Copyright (c) Ian T Nabney (1996-9) Daniel@0:
David J Evans (1998) Daniel@0: Daniel@0: Daniel@0: