Many visual learning tasks are usually confronted by some common diiculties. One of them is the lack of supervised information, due to the fact that labeling could be tedious, expensive or even impossible. Such scenario makes it challenging to learn object concepts from images. This problem could be alleviated by taking a hybrid of labeled and unlabeled training data for learning. Since the unl...

Several phenomenological approaches to quantum gravity predict the existence of a minimal measurable length and/or maximum momentum near Planck scale. When embedded into framework mechanics, such constraints induce modification canonical commutation relations and thus generalization Heisenberg uncertainty relations, commonly referred as generalized principle (GUP). Different models imply differ...