作者: José Mira , Ana E. Delgado , María T. López , Antonio Fernández-Caballero , Miguel A. Fernández
DOI: 10.1016/J.NEUCOM.2007.10.005
关键词: Natural language 、 Cognition 、 Lateral inhibition 、 Artificial intelligence 、 Conceptual model (computer science) 、 Semantic gap 、 Conceptual frame 、 Operationalization 、 Computer science
摘要: An important problem in artificial intelligence (AI) is to find calculation procedures save the semantic gap between analytic formulations of neuronal models and concepts natural language used describe cognitive processes. In this work we explore a way saving for case attentional processes, consisting (1) proposing first place conceptual model attention double bottom-up/top-down organization, (2) afterwards neurophysiological cortical sub-cortical involved structures, (3) establishing correspondences entities (2), (4) operationalizing by using biologically inspired mechanisms (algorithmic lateral inhibition accumulative computation) formulated at symbolic level, and, (5) assessing validity proposal accommodating works research team on diverse aspects associated visual surveillance tasks. The results obtained support reasonable enable its application tasks different from ones considered work. particular, when linking geometric descriptions scene with corresponding activity level.