Daniel@0: Daniel@0: Daniel@0: Daniel@0: Netlab Reference Manual mdninit Daniel@0: Daniel@0: Daniel@0: Daniel@0:

mdninit Daniel@0:

Daniel@0:

Daniel@0: Purpose Daniel@0:

Daniel@0: Initialise the weights in a Mixture Density Network. Daniel@0: Daniel@0:

Daniel@0: Synopsis 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:

Daniel@0: Description 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:

Daniel@0: See Also Daniel@0:

Daniel@0: mdn, mlp, mlpinit, gmminit
Daniel@0: Pages: Daniel@0: Index Daniel@0:
Daniel@0:

Copyright (c) Ian T Nabney (1996-9) Daniel@0:

David J Evans (1998) Daniel@0: Daniel@0: Daniel@0: