See this document in CiteSeerX!

Recent Results on Boolean Concept Learning (1987)  (Make Corrections)  (20 citations)
Michael Kearns Ming Li Harvard University and Ohio State University Leonard...
Proceedings of the Fourth International Workshop on Machine Learning



  Home/Search   Context   Related

 
View or download:
upenn.edu/~mkearns/paper...klpvml.ps.Z
Cached:  PS.gz  PS  PDF   Image  Update  Help

From:  upenn.edu/~mkearns/ (more)
(Enter author homepages)

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

Abstract: Recently, a new formal model of learnability was introduced [23]. The model is applicable to practical learning systems because it requires the learning algorithm to be feasibly computable, yet at the same time demands only that the algorithm find an approximation to the unknown rule. We survey recent results in this new area of theoretical induction, giving both positive (learnability) and negative (non-learnability) results, as well as outlining useful techniques for proving... (Update)

Context of citations to this paper:   More

...this result, for learning over the uniform distribution. Another important restriction of DNF is the class of monotone DNF. Kearns et al. KLPV87] have shown that under the PAC model, learning DNF reduces to learning monotone DNF. That is, if monotone DNF is PAC learnable, then...

.... learning theory (COLT) on the PAClearnability [Valiant, 1984] of boolean expressions, see for instance [Mitchell, 1997; Kearns et al. 1987] One of the results is the following (with a k term DNF being a DNF with at most k queries) k term DNF is not PAC learnable,...

Cited by:   More
Concepts and Autonomous Agents - Davidsson (1994)   (Correct)
From Propositional to First Order Logic in Machine Learning and.. - Van Laer (2002)   (Correct)
The Fourier Transform in Computational Learning Theory - Sun (1996)   (Correct)

Active bibliography (related documents):   More   All
0.5:   VC Dimension and Learnability of Sparse Polynomials and.. - Karpinski, Werther (1989)   (Correct)
0.4:   PAGODA: A Model for Autonomous Learning in Probabilistic Domains - desJardins (1992)   (Correct)
0.3:   On the Learnability of Boolean Formulae - Michael Kearns Harvard (1987)   (Correct)

Similar documents based on text:   More   All
0.3:   [Tou89] David Touretsky. - Advances In Neural   (Correct)
0.1:   Cryptographic Limitations on Learning Boolean Formulae and.. - Kearns, Valiant (1989)   (Correct)
0.1:   Learning Conjunctions of Horn Clauses - Angluin, Frazier, Pitt (1992)   (Correct)

Related documents from co-citation:   More   All
8:   Communications of the ACM (context) - Valiant, of et al. - 1984
8:   Statistical generalization of performance-related heuristics for knowledge-lean .. - Ieumwananonthachai, Wah - 1996
7:   A theory of the learnable (context) - Valiant - 1984

BibTeX entry:   (Update)

Kearns, M., Li, M., Pitt, L., & Valiant, L. G. (1987). Recent results on Boolean concept learning. Proceedings of the Fourth International Workshop on Machine Learning (pp. 337--352). Irvine, CA: Morgan Kaufmann. http://citeseer.ist.psu.edu/kearns87recent.html   More

@inproceedings{ kearns87recent,
    author = "M. Kearns and M. Li and L. Pitt and L. Valiant",
    title = "Recent Results on Boolean Concept Learning",
    booktitle = "Proceedings of the Fourth International Workshop on Machine Learning",
    publisher = "(published by Morgan Kaufmann, Los Altos California)",
    address = "Irvine, California",
    pages = "337--352",
    year = "1987",
    url = "citeseer.ist.psu.edu/kearns87recent.html" }
Citations (may not include all citations):
4212   Computers and Intractability: A Guide to the Theory of NPCom.. (context) - Garey, Johnson - 1979
537   A Theory of the Learnable (context) - Valiant - 1984
412   Language Identification in the Limit (context) - Gold - 1967
244   Learning Regular Sets From Queries and Counter-examples (context) - Angluin - 1986
215   Learning Decision-Lists - Rivest - 1986
144   Computational Limitations on Learning From Examples (context) - Pitt, Valiant - 1986
142   Finding Patterns Common to a Set of Strings (context) - Angluin - 1980
121   Learning Structural Descriptions from Examples (context) - Winston - 1975
84   Learning Disjunctions of Conjunctions (context) - Valiant - 1985
78   the Learnability of Boolean Formulae - Kearns, Li et al. - 1987
74   Inference of Reversible Languages (context) - Angluin - 1982
48   Classifying Learnable Geometric Concepts With the Vapnik-Che.. (context) - Blumer, Ehrenfeucht et al. - 1986
12   Polynomial Time Inference of Pattern Languages and its Appli.. (context) - Shinohara - 1982
11   Deductive Learning (context) - Valiant - 1984
10   Space Efficient Learning Algorithms (context) - Haussler - 1986
10   Acquisition of Appropriate Bias for Inductive Concept Learni.. (context) - Utgoff, Mitchell - 1982
8   Quantifying the Inductive Bias in Concept Learning (context) - Haussler - 1986
4   Types of Queries for Concept Learning (context) - Angluin - 1986
3   CNF Formulas From Noisy Examples (context) - Angluin, Laird - 1986
2   UC Santa Cruz (context) - Blumer, Ehrenfeucht et al. - 1986
1   How to Construct Random Functions (context) - Goldriech, Goldwasser et al. - 1984
1   Polynomial Time Inference of Extended Pattern Languages (context) - Shinohara - 1982
1   An Effective Model for Grammar Inference (context) - Crespi-Reghizzi - 1972
1   Unpublished course notes for Formal Models of Machine Infere.. (context) - Pitt



The graph only includes citing articles where the year of publication is known.


Documents on the same site (http://www.cis.upenn.edu/~mkearns/):   More
Graphical Economics - Sham Kakade Michael   (Correct)
Efficient Algorithms for Learning to Play Repeated Games Against.. - al. (1995)   (Correct)
On the Boosting Ability of Top-Down Decision Tree Learning.. - Kearns (1996)   (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