IDENTIFIABILITY OF HIDDEN MARKOV INFORMATION-SOURCES AND THEIR MINIMUM DEGREES OF FREEDOM

被引：69

作者：

ITO, H

AMARI, SI

KOBAYASHI, K

机构：

[1] UNIV ELECTROCOMMUN,DEPT COMP SCI & INFORMAT MATH,CHOFU,TOKYO 182,JAPAN

[2] UNIV TOKYO,DEPT MATH ENGN & INFORMAT PHYS,7-3-1 HONGO,BUNKYO KU,TOKYO 113,JAPAN

来源：

IEEE TRANSACTIONS ON INFORMATION THEORY | 1992年 / 38卷 / 02期

关键词：

FUNCTION PROCESS; HIDDEN MARKOV; IDENTIFIABILITY PROBLEM; MINIMUM DEGREE OF FREEDOM;

D O I：

10.1109/18.119690

中图分类号：

TP [自动化技术、计算机技术];

学科分类号：

0812 ;

摘要：

If it is observed only a function of the state in a finite-state Markov chain, then the stochastic process is no longer Markovian in general. This type of information source is found widely and the basic problem of their identifiability has remained open, that is, (he problem of showing when two different Markov chains generate the same stochastic process. The identifiability problem is completely solved by linear algebra, where a block structure of a Markov transition matrix plays a fundamental role, and from which the minimum degree of freedom for a source is revealed.

引用

页码：324 / 333

页数：10

共 31 条

[1] DIFFERENTIAL GEOMETRY OF A PARAMETRIC FAMILY OF INVERTIBLE LINEAR-SYSTEMS - RIEMANNIAN METRIC, DUAL AFFINE CONNECTIONS, AND DIVERGENCE [J].