MAP model selection for context trees

T.J. Tjalkens; F.M.J. Willems

doi:10.1109/MLSP.2006.275535

MAP model selection for context trees

T.J. Tjalkens, F.M.J. Willems

Signal Processing Systems

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution › Academic › peer-review

1 Citation (Scopus)

Abstract

Context tree models are Markov models where the conditioning is a string of previous symbols of variable length. These models are applicable for the modelling of natural languages and computer data. Also a decision tree can be seen as a context tree model. In this paper we derive an efficient method to determine the Maximum A-posteriori Probability model from a large set of context trees.

Original language	English
Title of host publication	Proc. of the 2006 IEEE Signal Processing Workshop
Place of Publication	Piscataway
Publisher	Institute of Electrical and Electronics Engineers
Pages	129-134
Number of pages	6
ISBN (Print)	1-4244-0656-0
DOIs	https://doi.org/10.1109/MLSP.2006.275535
Publication status	Published - 2006
Event	16th IEEE International Workshop on Machine Learning for Signal Processing, MLSP 2006 - Arlington, United States Duration: 6 Sept 2006 → 8 Sept 2006 Conference number: 16 http://mlsp2006.conwiz.dk/

Conference

Conference	16th IEEE International Workshop on Machine Learning for Signal Processing, MLSP 2006
Abbreviated title	MLSP 2006
Country/Territory	United States
City	Arlington
Period	6/09/06 → 8/09/06
Internet address	http://mlsp2006.conwiz.dk/

Access to Document

10.1109/MLSP.2006.275535

Cite this

@inproceedings{06e5d75033f94a6dafff4563edf7d891,

title = "MAP model selection for context trees",

abstract = "Context tree models are Markov models where the conditioning is a string of previous symbols of variable length. These models are applicable for the modelling of natural languages and computer data. Also a decision tree can be seen as a context tree model. In this paper we derive an efficient method to determine the Maximum A-posteriori Probability model from a large set of context trees.",

author = "T.J. Tjalkens and F.M.J. Willems",

year = "2006",

doi = "10.1109/MLSP.2006.275535",

language = "English",

isbn = "1-4244-0656-0",

pages = "129--134",

booktitle = "Proc. of the 2006 IEEE Signal Processing Workshop",

publisher = "Institute of Electrical and Electronics Engineers",

address = "United States",

note = "16th IEEE International Workshop on Machine Learning for Signal Processing, MLSP 2006, MLSP 2006 ; Conference date: 06-09-2006 Through 08-09-2006",

url = "http://mlsp2006.conwiz.dk/",

}

TY - GEN

T1 - MAP model selection for context trees

AU - Tjalkens, T.J.

AU - Willems, F.M.J.

N1 - Conference code: 16

PY - 2006

Y1 - 2006

N2 - Context tree models are Markov models where the conditioning is a string of previous symbols of variable length. These models are applicable for the modelling of natural languages and computer data. Also a decision tree can be seen as a context tree model. In this paper we derive an efficient method to determine the Maximum A-posteriori Probability model from a large set of context trees.

AB - Context tree models are Markov models where the conditioning is a string of previous symbols of variable length. These models are applicable for the modelling of natural languages and computer data. Also a decision tree can be seen as a context tree model. In this paper we derive an efficient method to determine the Maximum A-posteriori Probability model from a large set of context trees.

U2 - 10.1109/MLSP.2006.275535

DO - 10.1109/MLSP.2006.275535

M3 - Conference contribution

SN - 1-4244-0656-0

SP - 129

EP - 134

BT - Proc. of the 2006 IEEE Signal Processing Workshop

PB - Institute of Electrical and Electronics Engineers

CY - Piscataway

T2 - 16th IEEE International Workshop on Machine Learning for Signal Processing, MLSP 2006

Y2 - 6 September 2006 through 8 September 2006

ER -

MAP model selection for context trees

Abstract

Conference

Access to Document

Fingerprint

Cite this