Daniel@0: Daniel@0:
Daniel@0:Daniel@0: net = mdninit(net, prior) Daniel@0: net = mdninit(net, prior, t, options) Daniel@0:Daniel@0: Daniel@0: Daniel@0:
net = mdninit(net, prior)
takes a Mixture Density Network
Daniel@0: net
and sets the weights and biases by sampling from a Gaussian
Daniel@0: distribution. It calls mlpinit
for the MLP component of net
.
Daniel@0:
Daniel@0:
net = mdninit(net, prior, t, options)
uses the target data t
to
Daniel@0: initialise the biases for the output units after initialising the
Daniel@0: other weights as above. It calls gmminit
, with t
and options
Daniel@0: as arguments, to obtain a model of the unconditional density of t
. The
Daniel@0: biases are then set so that net
will output the values in the Gaussian
Daniel@0: mixture model.
Daniel@0:
Daniel@0:
mdn
, mlp
, mlpinit
, gmminit
Copyright (c) Ian T Nabney (1996-9) Daniel@0:
David J Evans (1998) Daniel@0: Daniel@0: Daniel@0: