Classifier Learning from Noisy Data as Probabilistic Evidence Combination

By S. W. Norton, H. Hirsh. 1992

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

Learning kernel logistic regression in the presence of class label noise (2014, background): “Most previous approaches try to detect mislabelled instances based on various heuristics, and very few take a principled modelling approach — with the notable exceptions of [32,24,25,36].”
Programming by Demonstration Using Version Space Algebra (2003, methodology): “Norton and Hirsh (1992) present an alternative method, where rather than maintaining a single version space containing potentially-inconsistent hypotheses, they maintain a set of version spaces, each of which is consistent with some interpretation of the data.”