(Enter summary)
Abstract: We introduce a rigorous performance criterion for training algorithms for probabilistic
automata (PAs) and hidden Markov models (HMMs), used extensively
for speech recognition, and analyze the complexity of the training problem as
a computational problem. The PA training problem is the problem of approximating
an arbitrary, unknown source distribution by distributions generated by
a PA. We investigate the following question about this important, well-studied
problem: Does there exist an... (Update)
Cited by: More
Learning Markov chains with variable memory length from noisy.. - Angluin, Csürös (1997)
(Correct)
PAC-learnability of Probabilistic Deterministic Finite State.. - Clark, Thollard (2004)
(Correct)
Grammatical Inference and First Language Acquisition - Alexander Clark Asc
(Correct)
Similar documents (at the sentence level):
58.4%: On the Computational Complexity of Approximating Distributions .. - Abe, Warmuth (1998)
(Correct)
44.6%: On the Computational Complexity of Approximating Distributions .. - Abe, Warmuth (1990)
(Correct)
Active bibliography (related documents): More All
0.2: Tagging English text with a probabilistic model - Merialdo (1993)
(Correct)
0.0: Probabilistic Finite-State Machines - Part II - Vidal, al.
(Correct)
0.0: Probably Approximately Correct Learning - Haussler (1990)
(Correct)
Similar documents based on text: More All
0.3: Polynomially Sparse Variations and Reducibility among.. - Abe, Watanabe (1992)
(Correct)
0.3: Characterizing PAC-learnability of Semilinear Sets - Abe (1998)
(Correct)
0.2: Tracking the Best Linear Predictor - Herbster (2001)
(Correct)
Related documents from co-citation: More All
25: A Tutorial on Hidden Markov Models and Selected Applications in Speech Recogniti.. (context) - Rabiner - 1989
20: Elements of Information Theory (context) - Cover, Thomas - 1991
17: the learnability of discrete distributions (context) - Kearns, Mansour et al. - 1994
BibTeX entry: (Update)
N. Abe and M. Warmuth. On the computational complexity of approximating distributions by probabilistic automata. Machine Learning, 9:205--260, 1992. http://citeseer.ist.psu.edu/article/abe90computational.html More
@inproceedings{ abe90computational,
author = "Naoki Abe and Manfred Warmuth",
title = "On the computational complexity of approximating distributions by probabilistic automata",
booktitle = "Proceedings of the Third Workshop on Computational Learning Theory",
publisher = "Morgan Kaufmann",
pages = "52--66",
year = "1990",
url = "citeseer.ist.psu.edu/article/abe90computational.html" }
Citations (may not include all citations):
537
A theory of the learnable (context) - Valiant - 1984
465
Learnability and the Vapnik-Chervonenkis dimension (context) - Blumer, Ehrenfeucht et al. - 1989
326
An inequality and associated maximization technique in stati.. (context) - Baum - 1972
318
Convergence of Stochastic Processes (context) - Pollard - 1984
145
Computational complexity of probabilistic Turing machines (context) - Gill - 1977
127
Complexity of automaton identification from given data (context) - Gold - 1978
115
Efficient distribution-free learning of probabilistic concep..
- Kearns, Schapire - 1990
103
An introduction to the application of the theory of probabil.. (context) - Levinson, Rabiner et al. - 1983
95
Coding and Information Theory (context) - Hamming - 1986
45
The minimum consistent DFA problem cannot be approximated wi.. (context) - Pitt, Warmuth - 1989
14
Identifying languages from stochastic examples (context) - Angluin - 1988
13
Generalizing the PAC model for neural net and other learning.. (context) - Haussler - 1989
3
Efficient unsupervised learning (context) - Laird - 1988
3
Minimum consistent 2-state DFA problem is NP-complete (context) - Angluin - 1989
2
the complexity of minimal inference of regular sets (context) - Angluin - 1978
2
The equivalence and learning of probabilistic automata (context) - Tzeng - 1989
2
A Proofs of Technical Lemmas In this appendix we prove the t.. (context) - Yamanishi, criterion et al.
The graph only includes citing articles where the year of publication is known.
Documents on the same site (http://www.cs.indiana.edu/pub/ucstri/index): More
Environment Modelling for Mobile Robots: Neural Learning for.. - van Dam (1998)
(Correct)
Broadcasting in Butterfly and DeBruijn Networks - Klasing, Monien, Peine, Stöhr (1992)
(Correct)
ILFA - A Project in Experimental Logic Computation - Dunker, Flögel, Büning..
(Correct)
Online articles have much greater impact More about CiteSeer.IST Add search form to your site Submit documents Feedback
CiteSeer.IST - Copyright Penn State and NEC