This paper presents an algorithm for extract ing propositions from trained neural networks. The algorithm is a decompositional approach which can be applied to any neural networ...
Many engineering disciplines can profitably use large high-resolution geometric models whose computational requirements exceed current computer hardware capacities. This paper pre...
This paper describes the spatial aggregation language and its applications. Spatial aggregation comprises a framework and a mechanism for organizing computations around image-like...
Christopher Bailey-Kellogg, Feng Zhao, Kenneth Yip
Most Artificial Intelligence programs lack generality because they reason with a single domain theory that is tailored for a specific task and embodies a host of implicit assumpti...
Weintroduce a parallel approach, "DT-SELECT," for selecting features used by inductive learning algorithms to predict protein secondary structure. DT-SELECTis able to ra...