Presentation 2008-03-12
Gaussian Graphical Model on Scale-Free Network
Takafumi USUI, Muneki YASUDA, Kazuyuki TANAKA,
PDF Download Page PDF download Page Link
Abstract(in Japanese) (See Japanese page)
Abstract(in English) We consider probabilistic inferences formulated by using Gaussian graphical models on scale free networks. We can derive the statistical performance for the probabilistic inference system by using the multi-dimensional Gaussian integral formulas. We extend the framework of the probabilistic inference to the hyperparameter estimation based on the EM algorithm. We calculate the statistical trajectories for the EM algorithms in the present probabilistic inference systems and compare the results for the scale free networks with the ones for regular graphs and random networks.
Keyword(in Japanese) (See Japanese page)
Keyword(in English) probabilistic inference / complex network / statistical learning / bayesian network / probabilistic information processing
Paper # NC2007-112
Date of Issue

Conference Information
Committee NC
Conference Date 2008/3/5(1days)
Place (in Japanese) (See Japanese page)
Place (in English)
Topics (in Japanese) (See Japanese page)
Topics (in English)
Chair
Vice Chair
Secretary
Assistant

Paper Information
Registration To Neurocomputing (NC)
Language JPN
Title (in Japanese) (See Japanese page)
Sub Title (in Japanese) (See Japanese page)
Title (in English) Gaussian Graphical Model on Scale-Free Network
Sub Title (in English)
Keyword(1) probabilistic inference
Keyword(2) complex network
Keyword(3) statistical learning
Keyword(4) bayesian network
Keyword(5) probabilistic information processing
1st Author's Name Takafumi USUI
1st Author's Affiliation Graduate School of Information Sciences, Tohoku University()
2nd Author's Name Muneki YASUDA
2nd Author's Affiliation Graduate School of Information Sciences, Tohoku University
3rd Author's Name Kazuyuki TANAKA
3rd Author's Affiliation Graduate School of Information Sciences, Tohoku University
Date 2008-03-12
Paper # NC2007-112
Volume (vol) vol.107
Number (no) 542
Page pp.pp.-
#Pages 5
Date of Issue