The power of amnesia: Learning probabilistic automata with variable memory length

Machine Learning

Volumn 25, Issue 2-3, 1996, Pages 117-149

  Ron, Dana ^a   Singer, Yoram ^b   Tishby, Naftali ^c  

^a MASSACHUSETTS INSTITUTE OF TECHNOLOGY   (United States)

^b AT AND T LABS RESEARCH   (United States)

^c HEBREW UNIVERSITY OF JERUSALEM   (Israel)

Author keywords

Learning distributions; Markov models; Probabilistic automata; Suffix trees; Text correction

Indexed keywords

COMPUTATIONAL COMPLEXITY; COMPUTATIONAL LINGUISTICS; DATA STORAGE EQUIPMENT; FINITE AUTOMATA; HUMAN COMPUTER INTERACTION; MARKOV PROCESSES; MATHEMATICAL MODELS; POLYNOMIALS; PROBABILITY; RANDOM PROCESSES;

ENGLISH LANGUAGE; LEARNING DISTRIBUTIONS; MARKOV MODELS; PROBABILISTIC SUFFIX AUTOMATA; SUFFIX TREES; TEXT CORRECTION;

LEARNING ALGORITHMS;

EID: 0030282113     PISSN: 08856125     EISSN: None     Source Type: Journal    
DOI: 10.1007/bf00114008     Document Type: Article

References (4)

1. Abe, N. & Warmuth, M. (1992). On the computational complexity of approximating distributions by probabilistic automata. Machine Learning, 9:205-260.
2. Baum, L.E. (1972). An inequality and associated maximization technique in statistical estimation for probabilistic functions of markov chains. Inequalities, 3:1-8.
3. Baum, L.E., Petrie, T., Soules, G. & Weiss, N. (1970). A maximization technique occuring in the statistical analysis of probabilistic functions of markov chains. Annals of Mathematical Statistics, 41 (1):164-171.
4. Fill, J.A. (1991). Eigenvalue bounds on convergence to stationary for nonreversible Markov chains, with an application to exclusion process. Annals of Applied Probability, 1:62-87.