Sustained emerging spatio-temporal co-occurrence patterns (SECOPs) represent subsets of object-types that are increasingly located together in space and time. Discovering SECOPs i...
Mete Celik, Shashi Shekhar, James P. Rogers, James...
We present and evaluate a method for estimating the relevance and calibrating the values of parameters of an evolutionary algorithm. The method provides an information theoretic m...
Rule extraction is a technique aimed at transforming highly accurate opaque models like neural networks into comprehensible models without losing accuracy. G-REX is a rule extract...
It is well-known that knowledgebases may contain inconsistencies. We provide a framework of measures, based on a first-order four-valued logic, to quantify the inconsistency of a ...
Abstract--For the last decade, we have developed a visionbased architecture for mobile robot navigation. Our bio-inspired model of the navigation has proved to achieve sensory-moto...