S. E. Decator. EÆcient Learning from Faulty Data. PhD thesis, Harvard University, 1995. Home/Search Document Not in Database Summary Related Articles |
This paper is cited in the following contexts:
Noise Tolerant Learnability via the Dual Learning Problem - Fine, Gilad-Bachrach.. (Correct)
....(SQ) and proved that if a class is learnable with SQs then it is also learnable in the presence of random labeling noise and presented a variety of problems in which this approach may be applied. Since Kearns pioneering paper, much work was done on the subject of learning in a noisy environment [6, 10], however, little is known regarding the properties which make a concept class robust to noise. In this study we try to characterize those conditions. We suggest two requirements: learnability and a density feature both of which, with respect to the dual learning problem. These requirements enable ....
S. E. Decator. EÆcient Learning from Faulty Data. PhD thesis, Harvard University, 1995.
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