2026-07-24T11:51:36Z https://drops.dagstuhl.de/oai

oai:drops-oai.dagstuhl.de:5349 2024-03-06T10:26:22Z ddc:004 open_access

Machine Learning with Interdependent and Non-identically Distributed Data (Dagstuhl Seminar 15152) Darrell, Trevor Kloft, Marius Pontil, Massimiliano Rätsch, Gunnar Rodner, Erik machine learning computer vision computational biology transfer learning domain adaptation One of the most common assumptions in many machine learning and data analysis tasks is that the given data points are realizations of independent and identically distributed (IID) random variables. However, this assumption is often violated, e.g., when training and test data come from different distributions (dataset bias or domain shift) or the data points are highly interdependent (e.g., when the data exhibits temporal or spatial correlations). Both scenarios are typical situations in visual recognition and computational biology. For instance, computer vision and image analysis models can be learned from object-centric internet resources, but are often rather applied to real-world scenes. In computational biology and personalized medicine, training data may be recorded at a particular hospital, but the model is applied to make predictions on data from different hospitals, where patients exhibit a different population structure. In the seminar report, we discuss, present, and explore new machine learning methods that can deal with non-i.i.d. data as well as new application scenarios. Schloss Dagstuhl – Leibniz-Zentrum für Informatik Trevor Darrell and Marius Kloft and Massimiliano Pontil and Gunnar Rätsch and Erik Rodner 2015 Is Part Of Dagstuhl Reports, Volume 5, Issue 4 (2015) Article Text doc-type:ResearchArticle publishedVersion application/pdf doi:10.4230/DagRep.5.4.18 urn:nbn:de:0030-drops-53497 https://drops.dagstuhl.de/entities/document/10.4230/DagRep.5.4.18 eng https://creativecommons.org/licenses/by/3.0/legalcode