Presentation | 1998/11/17 Learning Theory for Statistical models with singular points based on algebraic analysis Sumio Watanabe, |
---|---|
PDF Download Page | PDF download Page Link |
Abstract(in Japanese) | (See Japanese page) |
Abstract(in English) | Mathematical foundation for nonlinear and irregular statistical models such as multi-layer neural networks and gauussian mixutures have not been sufficiently established, because the set of true parameters of them is an algeraic variety with singularities. This paper proposes a method to clarify the general learning curves by measuring the depth of the singular points based on the theory for Sato's b-functions. |
Keyword(in Japanese) | (See Japanese page) |
Keyword(in English) | Irregular statistical model / Algebraic Analysis / Algebraic variety / Sato's b function |
Paper # | NC98-64 |
Date of Issue |
Conference Information | |
Committee | NC |
---|---|
Conference Date | 1998/11/17(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 | JPN |
Title (in Japanese) | (See Japanese page) |
Sub Title (in Japanese) | (See Japanese page) |
Title (in English) | Learning Theory for Statistical models with singular points based on algebraic analysis |
Sub Title (in English) | |
Keyword(1) | Irregular statistical model |
Keyword(2) | Algebraic Analysis |
Keyword(3) | Algebraic variety |
Keyword(4) | Sato's b function |
1st Author's Name | Sumio Watanabe |
1st Author's Affiliation | Advanced Information Processing Division P & I Laboratory, Tokyo Institute of Technology() |
Date | 1998/11/17 |
Paper # | NC98-64 |
Volume (vol) | vol.98 |
Number (no) | 401 |
Page | pp.pp.- |
#Pages | 8 |
Date of Issue |