Transfer learning has benefited many real-world applications where labeled data are abundant in source domains but scarce in the target domain. As there are usually multiple relevant domains where knowledge can be transferred, multiple source transfer learning (MSTL) has recently attracted much attention. However, we are facing two major challenges when applying MSTL. First, without knowledge a...

We propose a method called Topic Graph based NMF for Transfer Learning (TNT) based on Non-negative Matrix Factorization (NMF). Since NMF learns feature vectors to approximate the given data, the proposed approach tries to preserve the feature space which is spanned by the feature vectors to realize transfer learning. Based on the learned feature vectors in the source domain, a graph structure c...

Three experiments examined the effects of simultaneous and successive presentation on part/whole transfer in free recall. In the first two experiments, Ss received six or eight trials on the part list. The observed absence of negative transfer under any presentation condition was attributed to the fact that part-list subjective organization did not increase over reals. In Experiment III Ss rece...

When expert operators interact with a new device, they inevitably reuse former interaction modes and actions. This phenomenon is due to the human cognition seeking resources savings. Schemas support this strategy and are implemented in such a way that perfection is disregarded at the profit of an intuitive trade-off between performance and cognitive resources savings. As a consequence, humans h...