caa a22 4500 475800826 CHVBK 20180406123736.0 cr unu---uuuuu 170329e20001201xx s 000 0 eng 10.1023/A:1026567325853 doi (NATIONALLICENCE)springer-10.1023/A:1026567325853 Utsugi Akio National Institute of Bioscience and Human-Technology, 1-1 Higashi Tsukuba, 305-8566, Ibaraki, Japan aut Bayesian Sampling and Ensemble Learning in Generative Topographic Mapping [Elektronische Daten] [Akio Utsugi] Generative topographic mapping (GTM) is a statistical model to extract a hidden smooth manifold from data, like the self-organizing map (SOM). Although a deterministic search algorithm for the hyperparameters regulating the smoothness of the manifold has been proposed previously, it is based on approximations that are valid only on abundant data. Thus, it often fails to obtain suitable estimates on small data. In this paper, to improve the hyperparameter search in GTM, we construct a Gibbs sampler on the model, which generates random sample series following the posteriors on the hyperparameters. Reliable estimates are obtained from the samples. In addition, we obtain another deterministic algorithm using the ensemble learning. From the result of an experimental comparison of these algorithms, an efficient method for reliable estimation in GTM is suggested. Kluwer Academic Publishers, 2000 elastic net nationallicence evidence nationallicence Gibbs sampler nationallicence hyperparameter search nationallicence Laplace method nationallicence Markov chain Monte Carlo nationallicence self-organizing map nationallicence variational free energy nationallicence Neural Processing Letters Kluwer Academic Publishers 12/3(2000-12-01), 277-290 1370-4621 12:3<277 2000 12 11063 https://doi.org/10.1023/A:1026567325853 text/html Onlinezugriff via DOI 1 research-article jats NATIONALLICENCE 856 40 https://doi.org/10.1023/A:1026567325853 text/html Onlinezugriff via DOI NATIONALLICENCE 100 1- Utsugi Akio National Institute of Bioscience and Human-Technology, 1-1 Higashi Tsukuba, 305-8566, Ibaraki, Japan aut NATIONALLICENCE 773 0- Neural Processing Letters Kluwer Academic Publishers 12/3(2000-12-01), 277-290 1370-4621 12:3<277 2000 12 11063 Metadata rights reserved Springer special CC-BY-NC licence nationallicence BK010053 XK010053 XK010000 NATIONALLICENCE NATIONALLICENCE NL-springer