Abstract: In remote sensing image classification, active learning aims to learn a good classifier as best as possible by choosing the most valuable (informative and representative) training samples.

Unusually for an active-template synthesis, the metal binding site “lives on” in these rotaxanes. This was exploited in the synthesis of a molecular shuttle containing two different ligating sites in ...

Self-assembled supramolecular nanotubes of J-aggregated amphiphilic cyanine dye in aqueous solution are employed as chemically active templates for the photoinitiated formation of silver nanowires ...

MTL can be combined with other learning paradigms including semi-supervised learning, active learning, unsupervised learning, reinforcement learning, multi-view learning and graphical models. When the ...