Daniel@0: Daniel@0: Daniel@0: Daniel@0: Netlab Reference Manual gtmem Daniel@0: Daniel@0: Daniel@0: Daniel@0:

gtmem Daniel@0:

Daniel@0:

Daniel@0: Purpose Daniel@0:

Daniel@0: EM algorithm for Generative Topographic Mapping. Daniel@0: Daniel@0:

Daniel@0: Synopsis Daniel@0:

Daniel@0:

Daniel@0: 
Daniel@0: [net, options, errlog] = gtmem(net, t, options)
Daniel@0:

Daniel@0: Daniel@0: Daniel@0:

Daniel@0: Description Daniel@0:

Daniel@0: [net, options, errlog] = gtmem(net, t, options) uses the Expectation Daniel@0: Maximization algorithm to estimate the parameters of Daniel@0: a GTM defined by a data structure net. Daniel@0: The matrix t represents the data whose expectation Daniel@0: is maximized, with each row corresponding to a vector. It is assumed Daniel@0: that the latent data net.X has been set following a call to Daniel@0: gtminit, for example. Daniel@0: Daniel@0: The optional parameters have the following interpretations. Daniel@0: Daniel@0:

options(1) is set to 1 to display error values; also logs error Daniel@0: values in the return argument errlog. Daniel@0: If options(1) is set to 0, Daniel@0: then only warning messages are displayed. If options(1) is -1, Daniel@0: then nothing is displayed. Daniel@0: Daniel@0:

options(3) is a measure of the absolute precision required of the error Daniel@0: function at the solution. If the change in log likelihood between two steps of Daniel@0: the EM algorithm is less than this value, then the function terminates. Daniel@0: Daniel@0:

options(14) is the maximum number of iterations; default 100. Daniel@0: Daniel@0:

The optional return value options contains the final error value Daniel@0: (i.e. data log likelihood) in Daniel@0: options(8). Daniel@0: Daniel@0:

Daniel@0: Examples Daniel@0:

Daniel@0: The following code fragment sets up a GTM, initialises Daniel@0: the latent data sample and RBF Daniel@0: parameters from the data, sets the options and trains the model. Daniel@0:

Daniel@0: 
Daniel@0: % Create and initialise GTM model
Daniel@0: net = gtm(latentdim, nlatent, datadim, numrbfcentres, ...
Daniel@0:    'gaussian', 0.1);
Daniel@0: 
Daniel@0: options = foptions;
Daniel@0: options(1) = -1;
Daniel@0: options(7) = 1;    % Set width factor of RBF
Daniel@0: net = gtminit(net, options, data, 'regular', latentshape, [4 4]);
Daniel@0: 
Daniel@0: 
options = foptions;
Daniel@0: options(14) = 30;
Daniel@0: options(1) = 1;
Daniel@0: [net, options] = gtmem(net, data, options);
Daniel@0:

Daniel@0: Daniel@0: Daniel@0:

Daniel@0: See Also Daniel@0:

Daniel@0: gtm, gtminit

Daniel@0: Pages: Daniel@0: Index Daniel@0:

Daniel@0: