Kirchner, FrankEdgington, MarkMarkEdgington2020-03-092020-03-092016-09-09https://media.suub.uni-bremen.de/handle/elib/1121This dissertation presents a principled approach to representing and using instance-based knowledge. Perceptions and actions are probabilistically modelled in a unified structure which allows for simultaneous perception modelling and reasoning about desired actions. In particular, a new method for online instance-based learning of such models is presented and analyzed. This method, called Dynamic Gaussian Mixture Estimation (DGME), adapts a model's complexity to the process being modelled. The models produced by DGME are evaluated on several classification, prediction, and control applications, and its characteristics are compared with other state-of-the-art methods. In the context of control applications, an additional novel method, Gaussian Mixture Control (GMC), is introduced for precisely controlling systems that exhibit multimodality.enAlle Rechte vorbehaltenDensity EstimationOnline LearningBayesian LearningProbabilistic InferenceMixture ModelCognitive ModelingRobot Behavior and Control000 Informatik, Informationswissenschaft, allgemeine Werke::080 Allgemeine Sammelwerke, Zitatensammlungen::080 Allgemeine Sammelwerke, ZitatensammlungenDissertationurn:nbn:de:gbv:46-00105528-16