We study distribution-dependent, data-dependent, learning in the limit with adversarial disturbance. We consider an optimization-based approach to learning binary classifiers from...
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...
Data trees and data words have been studied extensively in connection with XML reasoning. These are trees or words that, in addition to labels from a finite alphabet, carry labels ...
Stochastic logic programs combine ideas from probabilistic grammars with the expressive power of definite clause logic; as such they can be considered as an extension of probabili...
While several hierarchical classification methods have been applied to web content, such techniques invariably rely on a pre-defined taxonomy of documents. We propose a new techni...