wolffd@0: mixparams = mdnfwd(net, x) wolffd@0: [mixparams, y, z] = mdnfwd(net, x) wolffd@0: [mixparams, y, z, a] = mdnfwd(net, x) wolffd@0:wolffd@0: wolffd@0: wolffd@0:
mixparams = mdnfwd(net, x) takes a mixture density network data
wolffd@0: structure net and a matrix x of input vectors, and forward
wolffd@0: propagates the inputs through the network to generate a structure
wolffd@0: mixparams which contains the parameters of several mixture models.
wolffd@0: Each row of x represents
wolffd@0: one input vector and the corresponding row of the matrices in mixparams
wolffd@0: represents the parameters of a mixture model for the conditional probability
wolffd@0: of target vectors given the input vector. This is not represented as an array
wolffd@0: of gmm structures to improve the efficiency of MDN training.
wolffd@0:
wolffd@0: The fields in mixparams are
wolffd@0:
wolffd@0: wolffd@0: type = 'mdnmixes' wolffd@0: ncentres = number of mixture components wolffd@0: dimtarget = dimension of target space wolffd@0: mixcoeffs = mixing coefficients wolffd@0: centres = means of Gaussians: stored as one row per pattern wolffd@0: covars = covariances of Gaussians wolffd@0: nparams = number of parameters wolffd@0:wolffd@0: wolffd@0: wolffd@0:
[mixparams, y, z] = mdnfwd(net, x) also generates a matrix y of
wolffd@0: the outputs of the MLP and a matrix z of the hidden
wolffd@0: unit activations where each row corresponds to one pattern.
wolffd@0:
wolffd@0:
[mixparams, y, z, a] = mlpfwd(net, x) also returns a matrix a
wolffd@0: giving the summed inputs to each output unit, where each row
wolffd@0: corresponds to one pattern.
wolffd@0:
wolffd@0:
mdn, mdn2gmm, mdnerr, mdngrad, mlpfwdCopyright (c) Ian T Nabney (1996-9) wolffd@0:
David J Evans (1998) wolffd@0: wolffd@0: wolffd@0: