Free energy of stochastic context free grammar on variational Bayes

被引：0
|
作者：
Hosino, Tikara
Watanabe, Kazuho
Watanabe, Sumio
机构：
[1] Tokyo Inst Technol, Midori Ku, Yokohama, Kanagawa 2268503, Japan
[2] Nihon Unisys Ltd, Koutou Ku, Tokyo 1358560, Japan
[3] Tokyo Inst Technol, Precis & Intelligence Lab, Midori Ku, Yokohama, Kanagawa 2268503, Japan
来源：
NEURAL INFORMATION PROCESSING, PT 1, PROCEEDINGS | 2006年 / 4232卷
关键词：
D O I：
暂无
中图分类号：
TP18 [人工智能理论];
学科分类号：
081104 ; 0812 ; 0835 ; 1405 ;
摘要：
Variational Bayesian learning is proposed for approximation method of Bayesian learning. In spite of efficiency and experimental good performance, their mathematical property has not yet been clarified. In this paper we analyze variational Bayesian Stochastic Context Free Grammar which includes the true distribution thus the model is non-identifiable. We derive their asymptotic free energy. It is shown that in some prior conditions, the free energy is much smaller than identifiable models and satisfies eliminating redundant non-terminals.
引用
收藏
页码：407 / 416
页数：10
相关论文
共 50 条
  • [1] An alternative view of variational Bayes and asymptotic approximations of free energy
    Watanabe, Kazuho
    MACHINE LEARNING, 2012, 86 (02) : 273 - 293
  • [2] An alternative view of variational Bayes and asymptotic approximations of free energy
    Kazuho Watanabe
    Machine Learning, 2012, 86 : 273 - 293
  • [3] STOCHASTIC CONTEXT-FREE GRAMMAR AND MARKOV CHAIN.
    Ozeki, Kazuhiko
    Systems - Computers - Controls, 1974, 5 (03): : 104 - 110
  • [4] Generalization errors in estimation of stochastic context-free grammar
    Yamazaki, K
    Watanabe, S
    PROCEEDINGS OF THE NINTH IASTED INTERNATIONAL CONFERENCE ON ARTIFICIAL INTELLIGENCE AND SOFT COMPUTING, 2005, : 183 - 188
  • [5] Using Variational Bayes free energy for unsupervised voice activity detection
    Cournapeau, David
    Kawahara, Tatsuya
    2008 IEEE INTERNATIONAL CONFERENCE ON ACOUSTICS, SPEECH AND SIGNAL PROCESSING, VOLS 1-12, 2008, : 4429 - 4432
  • [6] A stochastic context-free grammar model for time series analysis
    Wang, W.
    Portnoy, V.
    Pollak, L.
    2007 IEEE INTERNATIONAL CONFERENCE ON ACOUSTICS, SPEECH, AND SIGNAL PROCESSING, VOL III, PTS 1-3, PROCEEDINGS, 2007, : 1245 - +
  • [7] A stochastic context free grammar based framework for analysis of protein sequences
    Witold Dyrka
    Jean-Christophe Nebel
    BMC Bioinformatics, 10
  • [8] A stochastic context free grammar based framework for analysis of protein sequences
    Dyrka, Witold
    Nebel, Jean-Christophe
    BMC BIOINFORMATICS, 2009, 10 : 323
  • [9] Random Stimuli Generation Based on a Stochastic Context-Free Grammar
    Cekan, Ondrej
    Podivinsky, Jakub
    Kotasek, Zdenek
    2016 INTERNATIONAL CONFERENCE ON FIELD-PROGRAMMABLE TECHNOLOGY (FPT), 2016, : 295 - 296
  • [10] A UNIVERSAL ω-CONTEXT FREE GRAMMAR
    马世骅
    陈力行
    ScienceBulletin, 1987, (16) : 1146 - 1146
12345