wolffd@0: wolffd@0: wolffd@0: wolffd@0: Netlab Reference Manual mdninit wolffd@0: wolffd@0: wolffd@0: wolffd@0:

mdninit wolffd@0:

wolffd@0:

wolffd@0: Purpose wolffd@0:

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

wolffd@0: Synopsis wolffd@0:

wolffd@0:

wolffd@0: net = mdninit(net, prior)
wolffd@0: net = mdninit(net, prior, t, options)
wolffd@0:

wolffd@0: wolffd@0: wolffd@0:

wolffd@0: Description wolffd@0:

wolffd@0: wolffd@0:

net = mdninit(net, prior) takes a Mixture Density Network wolffd@0: net and sets the weights and biases by sampling from a Gaussian wolffd@0: distribution. It calls mlpinit for the MLP component of net. wolffd@0: wolffd@0:

net = mdninit(net, prior, t, options) uses the target data t to wolffd@0: initialise the biases for the output units after initialising the wolffd@0: other weights as above. It calls gmminit, with t and options wolffd@0: as arguments, to obtain a model of the unconditional density of t. The wolffd@0: biases are then set so that net will output the values in the Gaussian wolffd@0: mixture model. wolffd@0: wolffd@0:

wolffd@0: See Also wolffd@0:

wolffd@0: mdn, mlp, mlpinit, gmminit

wolffd@0: Pages: wolffd@0: Index wolffd@0:

wolffd@0:

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