—We propose an approach for improving object recognition and localization using spatial kernels together with instance embedding. Our approach treats each image as a bag of insta...
Abstract— This article presents an efficient and mature visionbased navigation algorithm based on a sensory-motor learning. Neither Cartesian nor topological map is required, bu...
Christophe Giovannangeli, Philippe Gaussier, Gael ...
Real-Time Strategy games present an interesting problem domain for Artificial Intelligence research. We review current approaches to developing AI systems for such games, noting th...
Abstract. In this paper we present a novel and general framework based on concepts of relational algebra for kernel-based learning over relational schema. We exploit the notion of ...
Adam Woznica, Alexandros Kalousis, Melanie Hilario
Understanding conceptual change is an important problem in modeling human cognition and in making integrated AI systems that can learn autonomously. This paper describes a model o...