Presentation | 2005/6/16 Learning Coefficient of Hidden Markov Models Keisuke YAMAZAKI, Sumio WATANABE, |
---|---|
PDF Download Page | PDF download Page Link |
Abstract(in Japanese) | (See Japanese page) |
Abstract(in English) | In information engineering, hidden Markov models (HMMs) are widely applied to speech recognition, natural language processing, gene analysis, etc. In spite of the enormous applications, the theoretical analysis of the performance is not yet sufficiently clarified because the models fall into singular models. In this paper, the Bayesian generalization error is derived in a mathematical rigorous way by using the algebraic geometrical method, which enables us to analyze singular models. |
Keyword(in Japanese) | (See Japanese page) |
Keyword(in English) | Hidden Markov models / Bayes generalization error / Algebraic geometry |
Paper # | NC2005-14 |
Date of Issue |
Conference Information | |
Committee | NC |
---|---|
Conference Date | 2005/6/16(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) | Learning Coefficient of Hidden Markov Models |
Sub Title (in English) | |
Keyword(1) | Hidden Markov models |
Keyword(2) | Bayes generalization error |
Keyword(3) | Algebraic geometry |
1st Author's Name | Keisuke YAMAZAKI |
1st Author's Affiliation | P&I Lab., Tokyo Institute of Technology() |
2nd Author's Name | Sumio WATANABE |
2nd Author's Affiliation | P&I Lab., Tokyo Institute of Technology |
Date | 2005/6/16 |
Paper # | NC2005-14 |
Volume (vol) | vol.105 |
Number (no) | 130 |
Page | pp.pp.- |
#Pages | 6 |
Date of Issue |