A key problem in reinforcement learning is finding a good balance between the need to explore the environment and the need to gain rewards by exploiting existing knowledge. Much ...
We present an architecture and an on-line learning algorithm and apply it to the problem of part-ofspeech tagging. The architecture presented, SNOW, is a network of linear separat...
In the context of meta-programming and reflective languages, classes are treated as full fledged objects which are instances of other classes named metaclasses. Metaclasses have p...
This paper describes an experiment to explore the effects of the TENCompetence infrastructure for supporting lifelong competence development which is now in development. This infra...
Computer-vision attention processes allocate computational resources to different parts of visual input and can lead to faster object recognition and image analysis. This paper p...