See this document in CiteSeerX!

k-Variable Pattern Languages Efficiently Stochastically Finite on Average from Positive Data (1998)  (Make Corrections)  
Peter Rossmanith, Thomas Zeugmann



  Home/Search   Context   Related

 
View or download:
i.kyushuu.ac.jp/~thoma...icgi98rz.ps.Z
flop.informatik.tumuenche...rz98.ps.gz
lti.informatik.rwthaache...icgi98rz.ps
Cached:  PS.gz  PS  PDF   Image  Update  Help

From:  i.kyushuu.ac.jp/~tho...altselect (more)
From:  wwwbrauer.informatik.tumue...pub
(Enter author homepages)

Rate this article: (best)
  Comment on this article  
(Enter summary)

Abstract: . The present paper presents a new approach of how to convert Gold-style [4] learning in the limit into stochastically finite learning with high confidence. We illustrate this approach on the concept class of all pattern languages. The transformation of learning in the limit into stochastically finite learning with high confidence is achieved by first analyzing the Lange--Wiehagen [7] algorithm with respect to its averagecase time behavior until convergence. This algorithm learns the class of... (Update)

Similar documents (at the sentence level):   More
43.1%:   Learning k-Variable Pattern Languages Efficiently.. - Rossmanith, Zeugmann (1998)   (Correct)
42.2%:   k-Variable Pattern Languages Efficiently Stochastically.. - Rossmanith, Zeugmann (1998)   (Correct)
22.8%:   Stochastic Finite Learning of The Pattern Languages - Peter Rossmanith Rossmani   (Correct)

Active bibliography (related documents):   More   All
0.3:   The VC-Dimension of Subclasses of Pattern Languages - Mitchell, Scheffer, Sharma, .. (1999)   (Correct)
0.2:   Learning One-Variable Pattern Languages Very.. - Erlebach.. (1997)   (Correct)
0.2:   Learning One-Variable Pattern Languages in Linear Average Time - Reischuk, Zeugmann (1997)   (Correct)

Similar documents based on text:   More   All
0.2:   Efficient Learning of One-Variable Pattern.. - Erlebach.. (1996)   (Correct)
0.1:   Analyzing the Average-Case Behavior of Conjunctive Learning .. - Reischuk, Zeugmann (1998)   (Correct)
0.1:   Learning by Erasing - Lange, Zeugmann (1996)   (Correct)

BibTeX entry:   (Update)

@misc{ rossmanith-kvariable,
  author = "Peter Rossmanith and Thomas Zeugmann",
  title = "k-Variable Pattern Languages Efficiently Stochastically Finite on Average
    from Positive Data",
  url = "citeseer.ist.psu.edu/77661.html" }
Citations (may not include all citations):
412   Language identification in the limit (context) - Gold - 1967
156   Inductive inference of formal languages from positive data (context) - Angluin - 1980
142   Finding patterns common to a set of strings (context) - Angluin - 1980
74   Formal Principles of Language Acquisition (context) - Wexler, Culicover - 1980
61   Polynomial-time inference of arbitrary pattern languages (context) - Lange, Wiehagen - 1991
36   A polynomial-time algorithm for learning k--variable pattern.. (context) - Kearns, Pitt - 1991
34   Pattern inference (context) - Shinohara, Arikawa - 1995
34   The Formal Language Theory Column - Salomaa, Return - 1994
31   the complexity of inductive inference (context) - Daley, Smith - 1986
24   Pattern languages are not learnable (context) - Schapire - 1990
22   DFAs and computational complexity (context) - Pitt - 1989
17   Learning string patterns and tree patterns from examples (context) - Ko, Marron et al. - 1990
8   Lange and Wiehagen's pattern learning algorithm: An averagec.. (context) - Zeugmann - 1998
8   variable pattern languages efficiently stochastically finite.. (context) - Rossmanith, Zeugmann - 1998

Documents on the same site (http://www.i.kyushu-u.ac.jp/~thomas/altselect.html):   More
Learning One-Variable Pattern Languages Very.. - Erlebach.. (1997)   (Correct)
Language Learning in Dependence on the Space of Hypotheses - Zeugmann (1993)   (Correct)
Learning One-Variable Pattern Languages in Linear Average Time - Reischuk, Zeugmann (1997)   (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