The goal of this research initiative is to construct large-scale computational modeling of how knowledge of the world emerges from the combination of innate mechanisms and visual experience. The ultimate goal is a ‘digital baby’ model which, through perception and interaction with the world, develops on its own representations of complex concepts that allow it to understand the world around it, in terms of objects, object categories, events, agents, actions, goals, social interactions, etc. A wealth of empirical research in the cognitive sciences have studied how natural concepts in these domains are acquired spontaneously and efficiently from perceptual experience, but a major open challenge is an understating of the processes and computations involved by rigorous testable models.To deal with this challenge we propose a novel methodology based on two components. The first, ‘computational Nativism’, is a computational theory of cognitively and biologically plausible innate structures , which guide the system along specific paths through its acquisition of knowledge, to continuously acquire meaningful concepts, which can be significant to the observer, but statistically inconspicuous in the sensory input. The second, ‘embedded interpretation’ is a new way of acquiring extended learning and interpretation processes. This is obtained by placing perceptual inference mechanisms within a broader perception-action loop, where the actions in the loop are not overt actions, but internal operation over internal representation. The results will provide new modeling and understanding of the age-old problem of how innate mechanisms and perception are combined in human cognition, and may lay foundation for a major research direction dealing with computational cognitive development.