Yasubumi Sakakibara. Algorithmic Learning of Formal Languages and Decision Trees. PhD thesis, Tokyo Institute of Technology, October 1991. Research Report IIAS-RR-91-22E, International Institute for Advanced Study of Social Information Science, Fujitsu Laboratories, Ltd. Home/Search Document Not in Database Summary Related Articles Check |
This paper is cited in the following contexts:
Efficient Noise-Tolerant Learning From Statistical Queries - Kearns (1993) (100 citations) (Correct)
....for experimental machine learning research. Angluin and Laird provided an algorithm for learning boolean conjunctions that tolerates a noise rate approaching the information theoretic barrier of 1=2. Subsequently, there have been some isolated instances of efficient noisetolerant algorithms [14, 20, 22], but little work on characterizing which classes can be efficiently learned in the presence of noise, and no general transformations of Valiant model algorithms into noise tolerant algorithms. The primary contribution of the present paper is in making significant progress in both of these areas. ....
....1 Gamma ffi satisfies error(h) ffl. This probability is taken over the random draws from D made by EX (f; D) and any internal randomization of L. We call ffl the accuracy parameter and ffi the confidence parameter. 3 The Classification Noise Model The well studied classification noise model [1, 15, 11, 24, 14, 20, 22] is an extension of the Valiant model intended to capture the simplest type of white noise in the labels seen by the learner. We introduce a parameter 0 j 1=2 called the noise rate, and replace the oracle EX (f; D) with the faulty oracle EX j CN (f; D) where the subscript is the acronym for ....
[Article contains additional citation context not shown here]
Yasubumi Sakakibara. Algorithmic Learning of Formal Languages and Decision Trees. PhD thesis, Tokyo Institute of Technology, October 1991. Research Report IIAS-RR-9122E, International Institute for Advanced Study of Social Information Science, Fujitsu Laboratories, Ltd.
Efficient Distribution-free Learning of Probabilistic Concepts - Kearns, Schapire (1993) (108 citations) (Correct)
....polynomial in 1= 1 Gamma 2j) in addition to the usual other parameters. This specifically answers an open question proposed by Rivest [24] concerning the learnability of decision lists in such a noisy setting. This problem of learning noisy decision lists was solved independently by Sakakibara [25]. Theorem 3.2 Let 2 [0; 1] be fixed, and let F n be a basis of functions. Then the p concept class of probabilistic decision lists over basis F n with converging probabilities is learnable with a model of probability (assuming both and F n are known) Specifically, this class can be ....
Yasubumi Sakakibara. Algorithmic Learning of Formal Languages and Decision Trees. PhD thesis, Tokyo Institute of Technology, October 1991. Research Report IIAS-RR-91-22E, International Institute for Advanced Study of Social Information Science, Fujitsu Laboratories, Ltd.
Efficient Distribution-free Learning of Probabilistic Concepts - Kearns, Schapire (1993) (108 citations) (Correct)
No context found.
Yasubumi Sakakibara. Algorithmic Learning of Formal Languages and Decision Trees. PhD thesis, Tokyo Institute of Technology, October 1991. Research Report IIAS-RR-91-22E, International Institute for Advanced Study of Social Information Science, Fujitsu Laboratories, Ltd.
Efficient Noise-Tolerant Learning From Statistical Queries - Kearns (1998) (100 citations) (Correct)
No context found.
Yasubumi Sakakibara. Algorithmic Learning of Formal Languages and Decision Trees. PhD thesis, Tokyo Institute of Technology, October 1991. Research Report IIAS-RR-91-22E, International Institute for Advanced Study of Social Information Science, Fujitsu Laboratories, Ltd.
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