There is a strong technological and economic push for higher education providers to adopt online learning strategies. This is driven, in part, by the requirement of industry for l...
Although recent studies have shown that unlabeled data are beneficial to boosting the image retrieval performance, very few approaches for image retrieval can learn with labeled a...
A typical goal for transfer learning algorithms is to utilize knowledge gained in a source task to learn a target task faster. Recently introduced transfer methods in reinforcemen...
After a classifier is trained using a machine learning algorithm and put to use in a real world system, it often faces noise which did not appear in the training data. Particularl...
Kernel learning plays an important role in many machine learning tasks. However, algorithms for learning a kernel matrix often scale poorly, with running times that are cubic in t...