Common-sense laws of the physical world are well understood by humans. Even two-month-old infants share this understanding. And yet we are unable to build an AI-system that can rival the common-sense abilities of a developing infant.
Learning through time and experience is important, but it is not the whole story. Princeton University researchers are contributing new insights to the ageold question of what may be innate in humans, and what may be learned.
Beyond that, they are defining new boundaries for what role perceptual data can play when it comes to artificial systems acquiring knowledge and how studies on babies can contribute to building better AI-systems that simulate the human mind.MORE