![]() In this paper, we formulate and address the problem of informed discovery of unknown unknowns of any given predictive model where unknown unknowns occur due to systematic biases in the training data. As the models are blind to such errors, input from an oracle is needed to identify these failures. Such errors or unknown unknowns are rooted in model incompleteness, and typically arise because of the mismatch between training data and the cases encountered at test time. ![]() Download a PDF of the paper titled Identifying Unknown Unknowns in the Open World: Representations and Policies for Guided Exploration, by Himabindu Lakkaraju and 3 other authors Download PDF Abstract:Predictive models deployed in the real world may assign incorrect labels to instances with high confidence.
0 Comments
Leave a Reply. |
AuthorWrite something about yourself. No need to be fancy, just an overview. ArchivesCategories |