wolffd@0: wolffd@0: wolffd@0: wolffd@0: Netlab Reference Manual gtm wolffd@0: wolffd@0: wolffd@0: wolffd@0:

gtm wolffd@0:

wolffd@0:

wolffd@0: Purpose wolffd@0:

wolffd@0: Create a Generative Topographic Map. wolffd@0: wolffd@0:

wolffd@0: Synopsis wolffd@0:

wolffd@0:

wolffd@0: net = gtm(dimlatent, nlatent, dimdata, ncentres, rbfunc)
wolffd@0: net = gtm(dimlatent, nlatent, dimdata, ncentres, rbfunc, prior)
wolffd@0:

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

wolffd@0: Description wolffd@0:

wolffd@0: wolffd@0:

net = gtm(dimlatent, nlatent, dimdata, ncentres, rbfunc), wolffd@0: takes the dimension of the latent space dimlatent, the wolffd@0: number of data points sampled in the latent space nlatent, the wolffd@0: dimension of the data space dimdata, the number of centres in the wolffd@0: RBF model ncentres, the activation function for the RBF wolffd@0: rbfunc wolffd@0: and returns a data structure net. The parameters in the wolffd@0: RBF and GMM sub-models are set by calls to the corresponding creation routines wolffd@0: rbf and gmm. wolffd@0: wolffd@0:

The fields in net are wolffd@0:

wolffd@0:   type = 'gtm'
wolffd@0:   nin = dimension of data space
wolffd@0:   dimlatent = dimension of latent space
wolffd@0:   rbfnet = RBF network data structure
wolffd@0:   gmmnet = GMM data structure
wolffd@0:   X = sample of latent points
wolffd@0:

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

net = gtm(dimlatent, nlatent, dimdata, ncentres, rbfunc, prior), wolffd@0: sets a Gaussian zero mean prior on the wolffd@0: parameters of the RBF model. prior must be a scalar and represents wolffd@0: the inverse variance of the prior distribution. This gives rise to wolffd@0: a weight decay term in the error function. wolffd@0: wolffd@0:

wolffd@0: See Also wolffd@0:

wolffd@0: gtmfwd, gtmpost, rbf, gmm

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

wolffd@0: