mdnfwd

Purpose

Forward propagation through Mixture Density Network.

Synopsis

mixes = mdnfwd(net, x)
[mixes, y, z] = mdnfwd(net, x)
[mixes, y, z, a] = mdnfwd(net, x)

Description

mixes = mdnfwd(net, x) takes a mixture density network data structure net and a matrix x of input vectors, and forward propagates the inputs through the network to generate an array mixes of output mixture models. Each row of x represents one input vector and the corresponding row of mixes represents the data structure vector of the corresponding mixture model for the conditional probability of target vectors.

[mixes, y, z] = mdnfwd(net, x) also generates a matrix y of the outputs of the MLP and a matrix z of the hidden unit activations where each row corresponds to one pattern.

[mixes, y, z, a] = mlpfwd(net, x) also returns a matrix a giving the summed inputs to each output unit, where each row corresponds to one pattern.

See Also

gmm, mdn, mdnerr, mdngrad, mlpfwd
Pages: Index

Copyright (c) Christopher M Bishop, Ian T Nabney (1996, 1997)