We study the problem of learning a classification task in which only a dissimilarity function of the objects is accessible. That is, data are not represented by feature vectors bu...
— This paper demonstrates a learning mechanism for complex tasks. Such tasks may be inherently expensive to learn in terms of training time and/or cost of obtaining each training...
The diversity of mobile devices and their limitations have raised many challenges for the actual deployment of mobile learning across institutions. The main objective of this work...
This work addresses the problem of efficiently learning action schemas using a bounded number of samples (interactions with the environment). We consider schemas in two languages-...
Adaptive Time Warp protocols in the literature are usually based on a pre-defined analytic model of the system, expressed as a closed form function that maps system state to cont...