Reinforcement learning promises a generic method for adapting agents to arbitrary tasks in arbitrary stochastic environments, but applying it to new real-world problems remains di...
ally related entity types, or classes, into higher level, more abstract types, as part of a hierarchical classi®cation scheme. graphy, generalization retains the notion of abstrac...
—Active learning can actively select or construct examples to label to reduce the number of labeled examples needed for building accurate classifiers. However, previous works of...
Injectivity is one of the important properties for functions while it is undecidable in general and decidable for linear treeless functions. In this paper, we show new sufficient c...
In Programming by Example [PBE, also sometimes called "Programming by Demonstration"] systems, the system records actions performed by a user in the interface, and produ...
Robert St. Amant, Henry Lieberman, Richard Potter,...