Presentation | 2007-07-25 On the Computation Approach of Learning Coefficients by Weighted Resolution of Singularities Takeshi MATSUDA, Sumio WATANABE, |
---|---|
PDF Download Page | PDF download Page Link |
Abstract(in Japanese) | (See Japanese page) |
Abstract(in English) | Learning models which do not satisfy a statistical asymptotic theory is called singular statistical models. It says that Bayes learning is valid to the singular model. In the Bayes learning, it is important computing average of A posteriori distribution. However, the computation is difficult. Therefore, MCMC method is widely used. In this paper, We introduce the theoretical way to evaluate the correctness of MCMC method. |
Keyword(in Japanese) | (See Japanese page) |
Keyword(in English) | singular model / weighted blowup / MCMC |
Paper # | NC2007-31 |
Date of Issue |
Conference Information | |
Committee | NC |
---|---|
Conference Date | 2007/7/17(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 | ENG |
Title (in Japanese) | (See Japanese page) |
Sub Title (in Japanese) | (See Japanese page) |
Title (in English) | On the Computation Approach of Learning Coefficients by Weighted Resolution of Singularities |
Sub Title (in English) | |
Keyword(1) | singular model |
Keyword(2) | weighted blowup |
Keyword(3) | MCMC |
1st Author's Name | Takeshi MATSUDA |
1st Author's Affiliation | Department of Computational Intelligence and Systems Science, Tokyo Institute of Technology() |
2nd Author's Name | Sumio WATANABE |
2nd Author's Affiliation | Precision and Intelligence Laboratory, Tokyo Institute of Technology |
Date | 2007-07-25 |
Paper # | NC2007-31 |
Volume (vol) | vol.107 |
Number (no) | 157 |
Page | pp.pp.- |
#Pages | 5 |
Date of Issue |