The Internet Archive has digitized a microfilm copy of this work. It may be possible to borrow a copy for reading.
Filters
Page 3070 of Mathematical Reviews Vol. , Issue 96e
[page]
1996
Mathematical Reviews
Preserved Fulltext
Here, learnability of families of recursive languages is studied when the learner obeys certain natural constraints. ...
Summary: “The present paper deals with the learnability of in- dexed families Y of uniformly recursive languages from positive data. ...
Page 5999 of Mathematical Reviews Vol. , Issue 94j
[page]
1994
Mathematical Reviews
Preserved Fulltext
The Internet Archive has digitized a microfilm copy of this work. It may be possible to borrow a copy for reading.
Here, learnability of families of recursive languages is studied when the learner obeys certain natural constraints. ...
Summary: “Language learnability is investigated in the Gold para- digm of inductive inference from positive data. Angluin gave a characterization of learnable families in this framework. ...
On the Learnability of Shuffle Ideals
[chapter]
2012
Lecture Notes in Computer Science
Preserved Fulltext
A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2012; you can also visit the original URL.
The file type is application/pdf.
Although PAC learning unrestricted regular languages is long known to be a very difficult problem, one might suppose the existence (and even an abundance) of natural efficiently learnable sub-families. ...
Their approach was to embed a specific family of regular languages (the piecewise-testable ones) in a Hilbert space via a kernel and to identify languages with hyperplanes. ...
Acknowledgments We thank Sarah Eisenstat for the construction reducing the alphabet size to 3 in the proof of Theorem 4 and the anonymous referees for their helpful comments. ...
doi:10.1007/978-3-642-34106-9_12
fatcat:wr55gysfkzg3redp2if5275hwe
Page 9245 of Mathematical Reviews Vol. , Issue 2001M
[page]
2001
Mathematical Reviews
Preserved Fulltext
The Internet Archive has digitized a microfilm copy of this work. It may be possible to borrow a copy for reading.
Studied, then, is the synthesis from indices for r.e. classes and for indexed families of recursive languages of various kinds of noise- tolerant language-learners for the corresponding classes or families ...
An index for an indexed family of recursive languages (by definition) gen- erates a sequence of decision procedures defining the family. F. ...
Hypothesis spaces for learning
2011
Information and Computation
Preserved Fulltext
A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2017; you can also visit the original URL.
The file type is application/pdf.
In this paper we survey some results in inductive inference showing how learnability of a class of languages may depend on the hypothesis space chosen. ...
We also discuss results which consider how learnability is effected if one requires learning using every suitable hypothesis space. ...
Acknowledgments We thank Frank Stephan for several helpful discussions and comments on the paper. We also thank the anonymous referees for several helpful comments. ...
doi:10.1016/j.ic.2010.11.016
fatcat:q3ulldldwrggpnfsmi6kh6hpqy
Hypothesis Spaces for Learning
[chapter]
2009
Lecture Notes in Computer Science
Preserved Fulltext
A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2017; you can also visit the original URL.
The file type is application/pdf.
In this paper we survey some results in inductive inference showing how learnability of a class of languages may depend on the hypothesis space chosen. ...
We also discuss results which consider how learnability is effected if one requires learning using every suitable hypothesis space. ...
Acknowledgments We thank Frank Stephan for several helpful discussions and comments on the paper. We also thank the anonymous referees for several helpful comments. ...
doi:10.1007/978-3-642-00982-2_4
fatcat:bu45q5mhqjfmpc6oreei4dlyky
A non-learnable class of E-pattern languages
2006
Theoretical Computer Science
Preserved Fulltext
A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2019; you can also visit the original URL.
The file type is application/pdf.
As the main result, our analysis yields a negative outcome for the full class of E-pattern languages -and even for the subclass of terminal-free E-pattern languages -if the corresponding terminal alphabet ...
We investigate the inferrability of E-pattern languages (also known as extended or erasing pattern languages) from positive data in Gold's learning model. ...
Angluin has introduced some criteria on indexed families that reduce learnability to a particular language theoretical aspect (cf. [2] ). ...
doi:10.1016/j.tcs.2005.10.017
fatcat:hwlcplsffzakzjmqnn4vmk2p3q
Prescribed learning of r.e. classes
2009
Theoretical Computer Science
Preserved Fulltext
A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2019; you can also visit the original URL.
The file type is application/pdf.
This work extends studies of Angluin, Lange and Zeugmann on the dependence of learning on the hypothesis space chosen for the language class in the case of learning uniformly recursive language classes ...
enumerable language classes. ...
They also thank the anonymous referees of this journal (Theoretical Computer Science) and of the conference Algorithmic Learning Theory (ALT) 2007 in Sendai for comments which helped in improving the paper ...
doi:10.1016/j.tcs.2009.01.011
fatcat:2hbw2g5gpvejzaxskf2b7m4etm
Page 5023 of Mathematical Reviews Vol. , Issue 96h
[page]
1996
Mathematical Reviews
Preserved Fulltext
The Internet Archive has digitized a microfilm copy of this work. It may be possible to borrow a copy for reading.
”
96h:68173 68T05 68Q45
Takada, Yuji (Takada, Yuji]
A hierarchy of language families learnable by regular language learning. ...
The hierarchy is defined inductively by controlling a certain type of even linear
96h:68177
grammars with languages in one family to yield languages in the next larger family. ...
Prescribed Learning of R.E. Classes
[chapter]
2007
Lecture Notes in Computer Science
Preserved Fulltext
A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2008; you can also visit the original URL.
The file type is application/pdf.
This work extends studies of Angluin, Lange and Zeugmann on the dependence of learning on the hypotheses space chosen for the class. ...
space of the same class) and uniform (like prescribed, but the learner has to be synthesized effectively from an index of the hypothesis space). ...
We also thank the anonymous referees of the conference Algorithmic Learning Theory (ALT) 2007 in Sendai for comments which helped improving the paper. ...
doi:10.1007/978-3-540-75225-7_9
fatcat:vhzwvfkbqnapbigiwcpxeupdqi
Language learning from stochastic input
1992
Proceedings of the fifth annual workshop on Computational learning theory - COLT '92
Preserved Fulltext
A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2017; you can also visit the original URL.
The file type is application/pdf.
Language learning from positive data in the ...
Acknowledgements The work of S. Kapur ...
This version yields, as a special case, Angluin's learner for the families of languages that are learnable from all texts (and not just from a set of texts of probability one). ...
doi:10.1145/130385.130419
dblp:conf/colt/KapurB92
fatcat:jake2vmeprh7lp7jie4zh3wnz4
The Synthesis of Language Learners
1999
Information and Computation
Preserved Fulltext
A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2019; you can also visit the original URL.
The file type is application/pdf.
Studied is the metaproblem of synthesizing from indices for r.e. classes and for indexed families of languages various kinds of language learners for the corresponding classes or families indexed. ...
An index for an indexed family of languages (by definition) is a procedure which generates a sequence of decision procedures defining the family. ...
Furthermore, the proofs of the positive results provide characterizations of corresponding noise-tolerantly learnable language classes. ...
doi:10.1006/inco.1998.2782
fatcat:bkrvheyrybgtlpg2d5azxxoh7q
Page 1114 of Mathematical Reviews Vol. , Issue 96b
[page]
1996
Mathematical Reviews
Preserved Fulltext
The Internet Archive has digitized a microfilm copy of this work. It may be possible to borrow a copy for reading.
These investigations turn out to be different from the previous investi- gations on learning indexed families of recursive languages and at times require new proof techniques. ...
By focusing on this fundamental aspect we discover some general and simple tools for the analysis of learnability tasks. ...
Learning indexed families of recursive languages from positive data: A survey
2008
Theoretical Computer Science
Preserved Fulltext
A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2019; you can also visit the original URL.
The file type is application/pdf.
One line of research focuses on indexed families of recursive languages -classes of recursive languages described in a representation scheme for which the question of membership for any string in any of ...
the given languages is effectively decidable with a uniform procedure. ...
Many thanks are also due to Robert Holte for his comments on a draft version. Both helped to improve the paper significantly. Sandra Zilles was supported by the Alberta Ingenuity Fund. ...
doi:10.1016/j.tcs.2008.02.030
fatcat:jzsqdyddvrbz3bhwxeukqnrty4
Language Learning from Texts: Mindchanges, Limited Memory, and Monotonicity
1995
Information and Computation
Preserved Fulltext
A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2018; you can also visit the original URL.
The file type is application/pdf.
Many separation results have a v ariant: If a criterion A can be separated from B, then often it is possible to nd a family L of languages such that L is A and B learnable, but while it is possible to ...
The paper explores language learning in the limit under various constraints on the number of mindchanges, memory, and monotonicity. ...
On the other hand, if A does not imply B, then there is a family of languages learnable according to A with 2 mind changes which still fails to be learnable according to B. ...
doi:10.1006/inco.1995.1170
fatcat:4ulb63nvdve6vki3bmaaqhs4ti
« Previous
Showing results 1 — 15 out of 4,140 results