We present a new family of subgradient methods that dynamically incorporate knowledge of the geometry of the data observed in earlier iterations to perform more informative gradie...
In this paper we investigate the relation between transfer learning in reinforcement learning with function approximation and supervised learning with concept drift. We present a n...
An architecture is described for designing systems that acquire and manipulate large amounts of unsystematized, or so-called commonsense, knowledge. Its aim is to exploit to the fu...
Learning the structure of graphical models is an important task, but one of considerable difficulty when latent variables are involved. Because conditional independences using hid...
In this paper, we address the question of what kind of knowledge is generally transferable from unlabeled text. We suggest and analyze the semantic correlation of words as a gener...