Representationandinference of spatial knowledgeplay a fundamentalrole in spatial reasoning,whichitself is an important componentof manyapplications such as GeographicInformationSy...
Knowledge transfer is widely held to be a primary mechanism that enables humans to quickly learn new complex concepts when given only small training sets. In this paper, we apply ...
The effectiveness of knowledge transfer using classification algorithms depends on the difference between the distribution that generates the training examples and the one from wh...
In this paper we investigate the relation between transfer learning in reinforcement learning with function approximation and supervised learning with concept drift. We present a n...