Abstract. Multiple-instance learning (MIL) allows for training classifiers from ambiguously labeled data. In computer vision, this learning paradigm has been recently used in many ...
— A central goal of robotics and AI is to be able to deploy an agent to act autonomously in the real world over an extended period of time. To operate in the real world, autonomo...
Unsupervised sequence learning is important to many applications. A learner is presented with unlabeled sequential data, and must discover sequential patterns that characterize th...
Two sets of multimedia learning materials were compared for their ability to promote learning of introductory computer programming The first set of materials was a sequentially na...
ABSTRACT In this paper, we report our experiments using a realworld image dataset to examine the effectiveness of Isomap, LLE and KPCA. The 1,897-image dataset we used consists of ...
Mei-Chen Yeh, I-Hsiang Lee, Gang Wu, Yi Wu, Edward...