See this document in CiteSeerX!

Noise Tolerant Algortihms for Learning and Searching (1995)  (Make Corrections)  
Javed Alexander Aslam



  Home/Search   Context   Related

 
View or download:
mit.edu/publicatio...TLCSTR657.ps.gz
Cached:  PS.gz  PS  PDF   Image  Update  Help

From:  mit.edu/publications/pubs/ps/ (more)
(Enter author homepages)

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

Abstract: We consider the problem of developing robust algorithms which cope with noisy data. In the Probably Approximately Correct model of machine learning, we develop a general technique which allows nearly all PAC learning algorithms to be converted into highly efficient PAC learning algorithms which tolerate noise. In the field of combinatorial algorithms, we develop techniques for constructing search algorithms which tolerate linearly bounded errors and probabilistic errors. (Update)

Similar documents (at the sentence level):   More
50.1%:   Noise Tolerant Algorithms for Learning and Searching - Aslam (1995)   (Correct)
15.2%:   General Bounds on Statistical Query Learning and PAC Learning .. - Aslam, Decatur (1993)   (Correct)
15.0%:   Improved Noise-Tolerant Learning and Generalized Statistical.. - Aslam, Decatur (1994)   (Correct)

Active bibliography (related documents):   More   All
0.8:   Three Thresholds for a Liar - Spencer, Winkler (1992)   (Correct)
0.4:   Playing By Searching: Two Strategies Against a Linearly Bounded.. - Pedrotti   (Correct)
0.2:   Solution of Ulam's Searching Game with Three Lies or an Optimal.. - Deppe (1998)   (Correct)

Similar documents based on text:   More   All
0.7:   Learning Algorithms with Applications to Robot Navigation and.. - Singh (1995)   (Correct)
0.4:   The Informational Complexity of Learning from Examples - Niyogi (1996)   (Correct)
0.4:   Learning from Imperfect Data in Theory and Practice - Slonim (1996)   (Correct)

BibTeX entry:   (Update)

@techreport{ aslam95noise,
    author = "J. A Aslam",
    title = "Noise Tolerant Algorithms for Learning and Searching",
    number = "MIT/LCS/TR-657",
    pages = "127",
    year = "1995",
    url = "citeseer.ist.psu.edu/article/aslam95noise.html" }
Citations (may not include all citations):
493   Communications of the ACM (context) - Valiant, of et al. - 1984
465   Learnability and the Vapnik-Chervonenkis dimension (context) - Blumer, Ehrenfeucht et al. - 1989
454   the uniform convergence of relative frequencies of events to.. (context) - Vapnik, Ya et al. - 1971
375   Probability inequalities for sums of bounded random variable.. (context) - Hoeffding - 1963
273   The strength of weak learnability - Schapire - 1990
180   Boosting a weak learning algorithm by majority - Freund - 1990
151   A general lower bound on the number of examples needed for l.. (context) - Ehrenfeucht, Haussler et al. - 1989
142   Learning from noisy examples (context) - Angluin, Laird - 1988
139   Ten Lectures on the Probabilistic Method (context) - Spencer - 1987
132   Fast probabilistic algorithms for Hamiltonian circuits and m.. (context) - Angluin, Valiant - 1979
123   the method of bounded differences (context) - McDiarmid - 1989
115   the density of families of sets (context) - Sauer - 1972
107   Efficient noise-tolerant learning from statistical queries - Kearns - 1993
94   Learning in the presence of malicious errors - Kearns, Li - 1988
84   Learning disjunctions of conjunctions (context) - Valiant - 1985
66   Computational learning theory: Survey and selected bibliogra.. (context) - Angluin - 1992
63   Weakly learning DNF and characterizing statistical query lea.. - Blum, Furst et al. - 1994
52   North Holland Publishing Company (context) - MacWilliams, Sloane et al. - 1977
52   Learning from Good and Bad Data (context) - Laird - 1988
37   Statistical queries and faulty PAC oracles - Decatur - 1993
37   An improved boosting algorithm and its implications on learn.. (context) - Freund - 1992
32   Cambridge Tracts in Theoretical Computer Science (context) - Anthony, Biggs et al. - 1992
32   Coping with errors in binary search procedures (context) - Rivest, Meyer et al. - 1980
27   Learning integer lattices (context) - Helmbold, Sloan et al. - 1992
22   Computing with unreliable information (context) - Feige, Peleg et al. - 1990
11   the sample complexity of weak learning (context) - Goldman, Kearns et al. - 1990
9   General bounds on the number of examples needed for learning.. (context) - Simon - 1993
9   Probability and Computing (context) - Spencer, Winkler et al. - 1992
8   Comparison-based search in the presence of errors (context) - Borgstrom, Kosaraju - 1993
8   The Design and Analysis of Efficient Learning Algorithms (context) - Schapire - 1992
5   Charles Scribner's Sons (context) - Ulam, Mathematician - 1976
4   Algorithmic Learning of Formal Languages and Decision Trees (context) - Sakakibara - 1991
4   line algorithms for 2-coloring hypergraphs via chip games - Aslam, Dhagat - 1993
4   Searching wih known error probability (context) - Pelc - 1989
4   On playing twenty questions with a liar - Dhagat, G'acs et al. - 1992
3   Searching with a non-constant number of lies (context) - Frazier - 1990

Documents on the same site (http://www.lcs.mit.edu/publications/pubs/ps/):   More
Maps: A Compiler-Managed Memory System for Raw Machines - Barua, Lee, Amarasinghe.. (1998)   (Correct)
A Technique for Constructing Highly-Available Services - Ladin, Liskov, Shrira (1987)   (Correct)
Design and Verification of Speculative Processors - Shen, Arvind (1998)   (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