Most of the existing active learning algorithms are based on the realizability assumption: The learner’s hypothesis class is assumed to contain a target function that perfectly c...
Training datasets for learning of object categories are often contaminated or imperfect. We explore an approach to automatically identify examples that are noisy or troublesome fo...
Anelia Angelova, Yaser S. Abu-Mostafa, Pietro Pero...
This paper describes a genetic learning system called SIA, which learns attributes based rules from a set of preclassified examples. Examples may be described with a variable numbe...
In this paper, we study the problem of learning in the presence of classification noise in the probabilistic learning model of Valiant and its variants. In order to identify the cl...
This paper describes Pairwise Bisection: a nonparametric approach to optimizing a noisy function with few function evaluations. The algorithm uses nonparametric reasoning about si...