Shai Fine, Ran Gilad-Bachrach, Shahar Mendelson, Naftali Tishby  Home/Search
Context
Related
| cs.huji.ac.il/labs/le...NoiseDual.ps.gz cs.huji.ac.il/~ranb/papers...main.ps.gz Cached: PS.gz PS PDF This document uses CoBlitz to cache paper downloads. If your firewall is blocking outgoing connections to port 3125, you can use these links to download local copies.
Image Update HelpPS.gz PS PDF From: cs.huji.ac.il/labs/learnin...shai (more) Homepages: S.Fine |
Rate this article:      (best)Comment on this article |
Abstract: . Much of the research in machine learning and neural computation assumes that the teacher gives the correct answers to the learning algorithm. However, in many cases this assumption is doubtful, since di erent sorts of noise may disable the learner from getting the correct answers all the time. The noise could be caused by noisy communication, human errors, measuring equipment and many other causes. In some cases, problems which are eÆciently learnable without noise, become hard to learn when... (Update)
Similar documents (at the sentence level):
60.4%: Knowledge Acquisition in Statistical Learning Theory - Fine (1999) (Correct)
10.1%: A Universal Noise Cleaning Procedure via the Dual.. - Fine.. (Correct)
Active bibliography (related documents): More All
0.3: Learning DNF Over The Uniform Distribution Using A Quantum.. - Bshouty, Jackson (1995) (Correct)
0.3: The Conditioning of Boundary Element Equations on Locally .. - Ainsworth, McLean, Tran (1998) (Correct)
0.1: Learning Fixed-dimension Linear Thresholds From Fragmented Data - Goldberg (1999) (Correct)
Similar documents based on text: More All
0.2: Noise Tolerant Learning Using Early Predictors - Fine, Gilad-Bachrach, Shamir, .. (1999) (Correct)
0.2: Learnability in Hilbert spaces with Reproducing Kernels - Mendelson (Correct)
0.1: Resource Bounded Measure and Learnability - Lindner, Schuler, Watanabe (1998) (Correct)
BibTeX entry: (Update)
@misc{ fine-noise,
author = "Shai Fine and Ran Gilad-Bachrach and Shahar Mendelson and Naftali Tishby",
title = "Noise Tolerant Learnability via the Dual Learning Problem",
url = "citeseer.ist.psu.edu/199796.html" }
Citations (may not include all citations):465 Learnability and the vapnik-chervonenkis dimension (context) - Blumer, Ehrenfeucht et al. - 1989
142 Learning from noisy examples (context) - Angluin, Laird - 1988
131 Combinatorial Geometry (context) - Pach, Agarwal - 1995
94 Learning in the presence of malicious errors - Kearns, Li - 1993
55 Elliptic Partial Di erential Equations of Second Order (context) - Gilbarg, Trudinger - 1998
46 Classical Banach Spaces (context) - Lindenstrauss, Tzafriri - 1979
23 cient noise-tolerant learning from statistical queries (context) - Kearns - 1993
20 Hardness results for neural network approximation problems - Bartlett, Ben-David - 1999
19 the sample complexity of pac-learning using random and chose.. - Eisenberg, Rivest - 1990
15 Noisetolerant distribution-free learning of general geomtric.. - Bshouty, Goldman et al. - 1996
12 Probabilistic methods in the geometry of banach spaces (context) - Pisier - 1986
3 Learnability in banach spaces with reproducing kernels (context) - Mendelson - 1999
3 volume 69 of Pure and Applied Mathematics series (context) - Adams - 1975
3 Learning with queries corrupted by classication noise - Jackson, Shamir et al. - 1999
3 Noise tolerant learning using early predictors - Fine, Gilad-Bachrach et al. - 1999
3 Prediction-preseving reducibility (context) - Pitt, Warmuth - 1990
2 Faithful Representations and Moments of Satisfaction: Probab.. (context) - Troyansky - 1998
1 cient Learning from Faulty Data (context) - Decator - 1995
Documents on the same site (http://www.cs.huji.ac.il/labs/learning/People/shai.html): More
Noise Tolerant Learning Using Early Predictors - Fine, Gilad-Bachrach, Shamir, .. (1999) (Correct)
Agnostic Classification of Markovian Sequences - El-Yaniv, Fine, Tishby (1998) (Correct)
Digit Recognition In Noisy Environments Via A Sequential.. - Fine, Saon, Gopinath (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