Open compound domain adaptation (OCDA) has emerged as a practical setting which considers single labeled source against of multi-modal unlabeled target data in order to generalize better on novel unseen domains. We hypothesize that an improved disentanglement domain-related and task-related factors dense intermediate layer features can greatly aid OCDA. Prior-arts attempt this indirectly by emp...

Selecting appropriate learning services for a learner from a large number of heterogeneous knowledge sources is a complex and challenging task. This chapter illustrates and discusses how Semantic Web technologies can be applied to e-learning system to help learner in selecting appropriate learning course or retrieving relevant information. It firstly presents the main features of e-learning sce...