Parallel and distributed information processing systems play an increasingly important role in artificial intelligence and computer science. In this article an approach to learnin...
It is well understood that the key for successful Semantic Web applications depends on the availability of machine understandable meta-data. We describe the Information Grid, a pr...
Although backpropagation ANNs generally predict better than decision trees do for pattern classification problems, they are often regarded as black boxes, i.e., their predictions c...
This paper proposes the use of constructive ordinals as mistake bounds in the on-line learning model. This approach elegantly generalizes the applicability of the on-line mistake ...
This paper is a July 1999 snapshot of a "whitepaper" that I've been working on. The purpose of the whitepaper, which I initially drafted in April 1999, was to formu...