Formal AI systems traditionally represent knowledge using logical formulas. We will show, however, that for certain kinds of information, a modelbased representation is more compa...
We present a connectionist architecture that supports almost instantaneous deductive and abductive reasoning. The deduction algorithm responds in few steps for single rule queries...
To obtain classification systems with both good generalizat`ion performance and efficiency in space and time, we propose a learning method based on combinations of weak classifiers...
We describe several RNC algorithms for generating graphs and subgraphs uniformly at random. For example, unlabelled undirected graphs are generated in O(lg3 n) time using O n2 lg3...
Inductive programming systems characteristically exhibit an exponential explosion in search time as one increases the size of the programs to be generated. As a way of overcoming ...