An ultimate goal of AI is to build end-to-end systems that interpret natural language, reason over the resulting logical forms, and perform actions based on that reasoning. This r...
We present sparse topical coding (STC), a non-probabilistic formulation of topic models for discovering latent representations of large collections of data. Unlike probabilistic t...
Abstract. In the context of the RoboCup Simulation League, we describe a new representation of a software agent’s visual perception (“scene”), well suited for case-based reas...
An image representation framework based on structured sparse model selection is introduced in this work. The corresponding modeling dictionary is comprised of a family of learned ...
Abstract. Ontology is a promising tool to model and reason about context information in pervasive computing environment. However, ontology does not support representation and reaso...