Download:
|
by Thomas Zeugmann
Annals of Mathematics and Artificial Intelligence
http://www.tcs.mu-luebeck.de/pages/thomas/amaifin96z.ps.Z
Add To MetaCart
Abstract:
The present paper deals with the best-case, worst-case and average-case behavior of Lange and Wiehagen's (1991) pattern language learning algorithm with respect to its total learning time. Pattern languages have been introduced by Angluin (1980) and are defined as follows: Let A = f0; 1; : ::g be any non--empty finite alphabet containing at least two elements. Furthermore, let X = fx i i 2 INg be an infinite set of variables such that A " X =;. Patterns are non--empty strings over A [ X. L(), the language generated by pattern is the set of strings which can be obtained by substituting non-null strings from A 3 for the variables of the pattern. Lange and Wiehagen's (1991) algorithm learns the class of all pattern languages in the limit from text. We analyze this algorithm with respect to its total learning time behavior, i.e., the overall time taken by the algorithm until convergence. For every pattern containing k different variables it is shown that the total learning time is O(jj 2 log jAj (jAj + k)) in the best-case and unbounded in the worst-case. Furthermore, we estimate the expectation of the total learning time. In particular, it is shown that Lange and Wiehagen's algorithm possesses an expected total learning time of O(2 k
Citations
|
624
|
Language identification in the limit
– Gold
- 1967
|
|
528
|
Queries and concept learning
– Angluin
- 1988
|
|
204
|
Formal Languages and their Relation to Automata
– Hopcroft, Ullman
- 1969
|
|
176
|
Finding patterns common to a set of strings
– Angluin
- 1980
|
|
108
|
Formal Principles of Language Acquisition
– Wexler, Culicover
- 1980
|
|
50
|
Editing by example
– Nix
- 1985
|
|
39
|
Polynomial-time inference of arbitrary pattern languages, New Generation Computing 8
– Lange, Wiehagen
- 1991
|
|
32
|
Knowledge acquisition from amino acid sequences by machine learning system BONSAI, Trans. Information Processing Society of Japan 35
– Shimozono, Shinohara, et al.
- 1994
|
|
32
|
Polynomial time inference of extended regular pattern languages
– Shinohara
- 1982
|
|
31
|
Types of monotonic language learning and their characterization
– Lange, Zeugmann
- 1992
|
|
28
|
On the complexity of inductive inference
– Daley, Smith
- 1986
|
|
23
|
A polynomial-time algorithm for learning k--variable pattern languages from examples
– Kearns, Pitt
- 1989
|
|
21
|
Monotonic versus non-monotonic language learning, in
– Lange, Zeugmann
- 1993
|
|
21
|
Incremental learning from positive data
– Lange, Zeugmann
- 1996
|
|
21
|
Characterizations of monotonic and dual monotonic language learning
– Zeugmann, Lange, et al.
- 1995
|
|
20
|
Set-driven and rearrangement-independent learning of recursive languages
– Lange, Zeugmann
- 1996
|
|
18
|
Inclusion is undecidable for pattern languages
– Jiang, Salomaa, et al.
- 1993
|
|
18
|
Ignoring data may be the only way to learn efficiently
– Wiehagen, Zeugmann
- 1994
|
|
14
|
MDL Learning of unions of simple pattern languages from positive examples
– Kilpelainen, Mannila, et al.
- 1995
|
|
14
|
Learning string patterns and tree patterns from examples
– Ko, Marron, et al.
- 1990
|
|
12
|
Return to patterns (The Formal Language Theory
– Salomaa
- 1994
|
|
11
|
Pattern languages are not learnable
– Schapire
- 1990
|
|
6
|
Learning pattern languages from a single initial example and from queries
– Marron
- 1988
|
|
5
|
Pattern inference, in "Algorithmic Learning for Knowledge-Based Systems
– Shinohara, Arikawa
- 1995
|
|
2
|
Learning unions of tree patterns using queries, Theoretical Computer Science 185
– Arimura, Ishizaka, et al.
- 1997
|
|
2
|
Learning data entry systems: An application of inductive inference of pattern languages
– Shinohara, Arikawa
- 1983
|
