D. Angluin and P. Laird. Learning from noisy examples. Machine Learning, 2(4):343--370, 1988.  Home/Search   Document Not in Database   Summary   Related Articles   Check

....m would solve the problem of learning DNF. Observe that the class considered by Frazier et al. is a generalization of the class of DNF formulas in which all variables only appear negated. While there has been some work addressing the general issue of mislabelled training examples in the PAC model [1, 18, 28, 17], there has been little research on learning geometric concepts with noise. Auer [3] investigates exact learning of boxes where some of the counterexamples, given in response to equivalence queries, are noisy. Auer shows that box n is learnable using hypotheses from box n if and only if the ....

Dana Angluin and Philip Laird. Learning from noisy examples. Machine Learning, 2(4):343--370, 1988.

....behavior on these datasets is almost the same. 5.2.3.2 Experiments with Increasing Noise Level In this section, noise tolerance of the FIL algorithms are investigated. There are two major types of noise that can be found in real world datasets: feature (attribute) noise, and classification noise [3, 11, 14, 24, 63]. Feature noise can be defined as incorrect feature value information. Classification noise involves corruption of the class label of an instance. Quinlan demonstrated that feature noise, occurring simultaneously in all features describing the instances, can result in faster degradation in ....

D. Angluin and P. Laird, Learning from Noisy Examples, Machine Learning, 2:343-370, 1988.

....affected with the addition of irrelevant features. 5.2.3.2 Experiments with Increasing Noise Level This section investigates the effect of noise in the datasets on the VFI algorithms compared to other algorithms. There are two major types of noise that can be found in real world datasets [3, 11, 15, 27, 69]: 1. Feature (attribute) noise, defined as incorrect feature value. 2. Classification noise, defined as incorrect class label of an instance. Quinlan demonstrated that feature noise, occurring simultaneously in all features describing the instances, can result in faster decrease in ....

....and the total votes are shown in the figure. The instance is predicted as class 2, which is the actual class predicted by the human expert. But the next highest vote, received by Feature values of test instance 1: F[1] 2 F[2] 3 F[3] 3 F[4] 3 F[5] 3 F[6] 0 F[7] 0 F[8] 0 F[9] 3 F[10] 3 F[11]:0 F[12] 0 F[13] 0 F[14] 0 F[15] 0 F[16] 0 F[17] 3 F[18] 2 F[19] 2 F[20] 3 F[21] 3 F[22] 3 F[23] 1 F[24] 3 F[25] 0 F[26] 0 F[27] 0 F[28] 0 F[29] 0 F[30] 0 F[31] 0 F[32] 1 F[33] 0 F[34] 34 Classes: 1] 2] 3] 4] 5] 6] ....

[Article contains additional citation context not shown here]

D. Angluin and P. Laird, Learning from Noisy Examples, Machine Learning, 2:343--370, 1988.

....system to determine how well it works in practice. In general, the additional work described in section 6.6 on monitoring is a good direction for future work. The most interesting direction for work on CARD is automatic derivation of dependencies. The idea here is to use either machine learning [AL88, Kea93, BHL91, KL88, Lit89] or association rule mining [AIS93, AS94] techniques to automatically determine dependencies. This approach requires having some monitored values that indicate if a system is up or down. Then, if we can show that any time component 1 is down, component 2 is also down, ....

Dana Angluin and Philip Laird. Learning from noisy examples. Machine Learning, 2(4):343--370, 1988.

....In fact, most of the standard PAC learning algorithms would fail if even a small number of the labelled examples given to the learning algorithm were noisy. Two popular noise models for both theoretical and experimental research are the classification noise model introduced by Angluin and Laird [2, 21] and the malicious error model introduced by Valiant [35] and further studied by Kearns and Li [20] In the classification noise model, each example received by the learner is mislabelled randomly and independently with some fixed probability. In the malicious error model, an adversary is allowed, ....

....In the malicious error model, an adversary is allowed, with some fixed probability, to substitute a labelled example of his choosing for the labelled example the learner would ordinarily see. While a limited number of eificient PAC algorithms had been developed which tolerate classification noise [2, 16, 26], no general framework for eflcient learning 1 in the presence of classification noise was known until Kearns introduced the Statistical Query model [19] 1Angluin and Laird [2] introduced a general framework for learning in the presence of classification noise. However, their methods do not ....

[Article contains additional citation context not shown here]

Dana Angluin and Philip Laird. Learning from noisy examples. Machine Learning, 2(4):343-370, 1988.

....In fact, most of the standard PAC learning algorithms would fail if even a small number of the labelled examples given to the learning algorithm were noisy. Two popular noise models for both theoretical and experimental research are the classification noise model introduced by Angluin and Laird [2, 21] and the malicious error model introduced by Valiant [35] and further studied by Kearns and Li [20] In the classification noise model, each example received by the learner is mislabelled randomly and independently with some fixed probability. In the malicious error model, an adversary is allowed, ....

....In the malicious error model, an adversary is allowed, with some fixed probability, to substitute a labelled example of his choosing for the labelled example the learner would ordinarily see. While a limited number of efficient PAC algorithms had been developed which tolerate classification noise [2, 16, 26], no general framework for efficient learning in the presence of classification noise was known until Kearns introduced the Statistical Query model [19] Angluin and Laird [2] introduced a general framework for learning in the presence of classification noise. However, their methods do not ....

[Article contains additional citation context not shown here]

Dana Angluin and Philip Laird. Learning from noisy examples. Machine Learning, 2(4):343--370, 1988.

.... is a lower bound on the allowed approximation error for every query made by L, the number of calls of EX(f;D) is O(d= 2 log 1= The reader should note that this result for the noise free PAC model has been extended to white noise PAC models: the Classi cation Noise model of Angluin and Laird [AL88]; the Constant Partition Classi cation Noise Model [Dec97] The proofs may be found in [Kea93] and [Dec97] Also note that almost all the concept classes known to be PAC learnable are SQ learnable and are therefore PAC learnable with classi cation noise. 3 Learning Monotone Conjunctions in the ....

D. Angluin and P. Laird. Learning from noisy examples. Machine Learning, 2(4):343370, 1988.

....papers have considered applications of vector quantization to estimation problems in classification, regression, and density estimation, our results appear to be novel. The problem is also related to learning from noisy examples , afforded from a theoretical point of view by Angluin and Laird [11] in the case of noise affecting a single bit. This paper can be summarized as follows. In Section II we explain the communication scenario, and the decoding as quantization. In Section III we introduce the estimations of the code parameters and of the number of noisy patterns to run an ....

D. Angluin and P. Laird, Learning from noisy examples, Machine Learning 2 343-370 (1988).

....the function f is derived from some function in the class C by adding noise to it. Typical works in this direction either tolerate only small amounts of noise [2, 42, 21, 39] i.e. that the function is modified only at a small fraction of all possible inputs) or assume that the noise is random [1, 26, 20, 25, 33, 13, 36] (i.e. that the decision of whether or not to modify the function at any given input is made by a random process) In contrast, we take the setting to an extreme, by considering a very large amount of (possibly adversarially chosen) noise. In particular, we consider situations in which the noise ....

Dana Angluin and Philip Laird. Learning from noisy examples. Machine Learning, 2(4):343-- 370, 1988.

....model replaces the (deterministic) classification of the examples supplied to the learner, by a random i.i.d. variable that has some fixed probability j of assuming the inverse of the true classification value, and with probability (1 Gamma j) assumes the correct classification value [21, 28, 2] (for a stronger model of noise see [18, 12] The task of providing methods by which efficient learning algorithms can be strengthened to noise tolerant ones is one of the most important in computational learning theory. As this task seems to be very difficult, one naturally seeks partial ....

Dana Angluin and Philip Laird. Learning from noisy examples. Machine Learning, 2(4):343--370, 1988.

....these results to apply to networks with piecewise linear hidden units. The earliest hardness results for agnostically learning simple classes address the problem of finding a hypothesis that maximizes the number of agreements (rather than just approximately maximizing it) Angluin and Laird [2] showed that maximizing agreements with monotone mono5 mials is NP hard. Kearns and Li [18] established a similar result for general monomials, and Hoffgen, Simon and Van Horn [16] for half spaces. One may argue, however, that for all practical purposes, a learner may be considered successful if ....

D. Angluin and P. D. Laird. Learning from noisy examples. Machine Learning, 2:343--370, 1988.

....randomly with probability d(x) if the label was 0 and with probability 1 Gamma d(x) if the label was 1 and finally outputting only the positively labeled sample points. There are some differences between this noisy PAC scenario and the common PAC classification noise model (see, for example, [AL88]) First we assume that the student receives, as input, only positively labeled examples (rather than revealing to the student all the drawn examples and providing him their labels) The second difference is that we allow the noise to depend upon the drawn example (rather then having a fixed ....

Dana Angluin and Philip Laird. Learning from noisy examples. Machine Learning, 2(4):343--370, 1988.

....of x according to the target function c t that the algorithm tries to learn. Since Valiant s seminal work, there were several attempts to relax these assumptions, by introducing models of noise. The first such noise model, called the Random Classification Noise model, was introduced in [2] and was extensively studied, e.g. in [1, 6, 9, 12, 13, 16] In this model the adversary, before providing each example (x; c t (x) to the learning algorithm tosses a biased coin; whenever the coin shows H , which happens with probability j, the classification of the example is flipped and so ....

D. Angluin and P. Laird, "Learning from Noisy Examples", Machine Learning, Vol. 2, pp. 343--370, 1988.

....query model Statistical query learning algorithms Simulators for noise free statistics ffl Choosing a best hypothesis in the statistical query model 20.2 The Statistical Query Model 20.2. 1 Motivation In the previous lecture, we examined the result derived by Angluin and Laird in [1] that PAC learning is possible even in the presence of classification noise, as long as we are able to find a hypothesis h 2 H which minimizes disagreement with a sample of bounded polynomial size. This finding was subject to the information theoretic barrier of 1=2 on the noise rate j. We also ....

Angluin, Dana, and Philip Laird. "Learning from noisy examples." Machine Learning, 2(4): 343-370, 1988.

No context found.

D. Angluin and P. Laird. Learning from noisy examples. Machine Learning, 2(4):343--370, 1988.

No context found.

D. Angluin, P. Laird. Learning from noisy examples. Machine Learning, 2(4), 1988, pp. 343-370.

No context found.

D. Angluin and P. Laird. Learning from Noisy Examples. Machine Learning, 2:343-370, 1988.

No context found.

Dana Angluin and Philip Laird. Learning from noisy examples. Machine Learning, 2(4):343-- 370, 1988.

No context found.

Dana Angluin and Philip Laird. Learning from noisy examples. Machine Learning, 2(4):343--370, 1988.

No context found.

D. Angluin, P. Laird. Learning from noisy examples. Machine Learning, 2, 1988, pp. 319-342.

No context found.

Dana Angluin, Philip Laird. Learning From Noisy Examples. In Machine Learning, 2(4) pp.343--370, 1988.

No context found.

D. Angluin and P. Laird. Learning from noisy examples. Machine Learning, 2(4):343-370, 1988.

No context found.

D. Angluin and P. Laird. Learning from noisy examples. Machine Learning, 2 (4), (1988), 471-479.

No context found.

D. Angluin and P. Laird. Learning from noisy examples. Machine Learning, 2 (4), (1988), 471-479.

No context found.

D. Angluin and P. Laird. Learning from noisy examples. Machine Learning, 2(4):343-370, 1988.

First 50 documents  Next 50

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