See this document in CiteSeerX!

On The Sample Complexity Of Pac-Learning Using Random And Chosen Examples (1991)  (Make Corrections)  (19 citations)
Bronwyn Bonnie Eisenberg



  Home/Search   Context   Related

 
View or download:
mit.edu/publicatio...MITLCSTR535.pdf
Cached:  PS.gz  PS  PDF   Image  Update  Help
Problem Downloading?
From:  mit.edu/publications/pubs/pdf/ (more)
(Enter author homepages)

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

Abstract: Two protocols used for learning under the pac-learning model introduced by Valiant are learning from random examples and learning from membership queries. Membership queries have also been used to efficiently and exactly learn a concept class that is too difficult to pac-learn using random examples. We ask whether using membership queries-- in conjunction with or instead of random examples serve a new purpose: helping to reduce the total number of examples needed to pac-learn a concept class C... (Update)

Context of citations to this paper:   More

...the other patterns, and still recover the same final hypothesis. Theoretical results and artificial examples discussed in Rivest and Eisenberg (1990) show that it is possible to invent malicious distributions for which the number of queries is comparable to the sample size,...

...problem. 3 Dense Learning Problems A learning problem is dense if every hypothesis has many hypotheses which are close but not equal to it [4]: Definition 1 A learning problem h Omega ; Hi is dense with respect to the probability measure D if for every h 2 H and every ffl 0...

Cited by:   More
Journal of Machine Learning Research 6 (2005) 1579--1619.. - With Online And (2005)   (Correct)
Incremental Learning with Sample Queries - Ratsaby (1998)   (Correct)
Active Learning in Neural Networks - Hasenjäger, Ritter   (Correct)

Active bibliography (related documents):   More   All
0.6:   Learning by Distances - Ben-David, Itai, Kushilevitz (1990)   (Correct)
0.3:   Pac Learning, Noise, and Geometry - Sloan   (Correct)
0.2:   Recent Results on Boolean Concept Learning - Michael Kearns Ming (1987)   (Correct)

Similar documents based on text:   More   All
0.5:   The Dual DFA Learning Problem: Hardness Results for Programming by .. - Cohen (1996)   (Correct)
0.4:   Algorithms For Approximate Graph Coloring - Blum (1991)   (Correct)
0.3:   More Efficient PAC-learning of DNF with Membership Queries Under.. - Bshouty (1999)   (Correct)

Related documents from co-citation:   More   All
15:   Queries and concept learning (context) - Angluin - 1988
11:   Learnability and the Vapnik Chervonenkis Dimension (context) - Blumer, Ehrenfeucht et al. - 1989
8:   Training connectionist networks with queries and selective sampling (context) - Cohn, Atlas et al. - 1990

BibTeX entry:   (Update)

B. Eisenberg. On the sample complexity of pac-learning using random and chosen examples. Master's thesis, Massachusetts Institute of Technology, 1991. http://citeseer.ist.psu.edu/eisenberg91sample.html   More

@techreport{ eisenberg92sample,
    author = "B. B. Eisenberg",
    title = "{ON} {THE} {SAMPLE} {COMPLEXITY} {OF} {PAC}-{LEARNING} {USING} {RANDOM} {AND} {CHOSEN} {EXAMPLES}",
    number = "MIT/LCS/TR-535",
    pages = "38",
    year = "1992",
    url = "citeseer.ist.psu.edu/eisenberg91sample.html" }
Citations (may not include all citations):
465   Learnability and the Vapnik-Chervonenkis dimension (context) - Blumer, Ehrenfeucht et al. - 1989  ACM   DBLP
441   Queries and concept learning (context) - Angluin - 1988  ACM   DBLP
348   Estimation of Dependences Based on Empirical Data (context) - Vapnik - 1982
244   Learning regular sets from queries and counterexamples (context) - Angluin - 1987  ACM   DBLP
215   Learning decision lists - Rivest - 1987  ACM   DBLP
184   Cryptographic limitations on learning boolean formulae and f.. - Kearns, Valiant - 1989
151   A gen- eral lower bound on the number of examples needed for.. (context) - Ehrenfeucht, Haussler et al. - 1989
144   Computational limitations on learning from ex- amples (context) - Pitt, Valiant - 1986
97   Learning read-once formulas with queries - Angluin, Hellerstein et al. - 1989  ACM   DBLP
83   Geometrical and statistical properties of systems of linear .. (context) - Cover - 1965
48   Classifying learnable geometric concepts with the Vapnik-Che.. (context) - Blumer, Ehrenfeucht et al. - 1986  ACM
26   How fast can a threshold gate learn (context) - Maass, Tur
26   On learning a union of half spaces (context) - Baum - 1990  ACM
25   Dover Publications (context) - Coxeter - 1973
20   Probably approximately correct learning - Haussler - 1990  ACM   DBLP
4   Types of queries for concept learning (context) - Angluin - 1986
3   Measurability constraints on pac learnability (context) - Ben-David, Benedek - 1991
1   Recent results in computational learning theory (context) - Pitt - 1990
1   A parametrization scheme for classifying models of learnabil.. (context) - Ben-David, Benedek et al. - 1989  ACM   DBLP
1   Communications of the AUM (context) - Valiant, of et al. - 1984



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


Documents on the same site (http://www.lcs.mit.edu/publications/pubs/pdf/):   More
Proving Correctness of a Distributed Shared Memory Implementation - Castro (1999)   (Correct)
Experience with Fine-Grain Synchronization in MIMD Machines.. - Yeung, Agarwal (1993)   (Correct)
Write Barrier Removal by Static Analysis - Zee, Rinard (2002)   (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