Stochastic complexities of hidden Markov models

2003 IEEE XIII Workshop on Neural Networks for Signal Processing (IEEE Cat. No.03TH8718) Pub Date : 2003-09-17 DOI:10.1109/NNSP.2003.1318017

Keisuke Yamazaki, Sumio Watanabe

引用次数: 16

Abstract

Hidden Markov models are now used in many fields, for example, speech recognition, natural language processing etc. However, the mathematical foundation of analysis for the models has not yet been constructed, since the HMMs are non-identifiable. In recent years, we have developed the algebraic geometrical method that allows us to analyze the non-regular and non-identifiable models. In this paper, we apply this method to the HMM and reveal the asymptotic order of its stochastic complexity in the mathematically rigorous way.

查看原文本刊更多论文

隐马尔可夫模型的随机复杂性

隐马尔可夫模型目前应用于许多领域，如语音识别、自然语言处理等。然而，模型分析的数学基础尚未建立，因为hmm是不可识别的。近年来，我们发展了代数几何方法，使我们能够分析非规则和不可识别的模型。本文将此方法应用于HMM，并以数学严谨的方式揭示了其随机复杂度的渐近阶。

本文章由计算机程序翻译，如有差异，请以英文原文为准。

求助全文

约1分钟内获得全文求助全文

来源期刊

2003 IEEE XIII Workshop on Neural Networks for Signal Processing (IEEE Cat. No.03TH8718)

自引率

0.00%

发文量