Agent WiSARD: A Hybrid System for Reconstructing and Understanding Two-dimensional Geometrical Figures

This paper investigates the integration of verbal and visual information for describing (explaining) the contents of images formed by two-dimensional geometrical figures, from a hybrid neurosymbolic perspective. The effectiveness of explanations provided by human beings is known to be often enhanced by multiple representation techniques, using both words and pictures. The latter seems particularly suitable in explanations concerning high-level visual tasks involving both-top-down reasoning and bottom-up perceptual processes.