Spontaneous acquisition of infant-level perceptual understanding

This project aims to develop computational models for spontaneous acquisition of infant-level perceptual understanding from realistic data in an unsupervised manner, i.e., without external guidance, similar to the development of such capabilities in early childhood. In particular, we are interested in building AI systems that can learn, with no external supervision, powerful and robust visual representations, which are useful for recognizing objects and understanding their interactions with the surroundings, including with other intelligent agents or objects. We believe that this learning ability will be an important step towards realizing artificial general intelligent (AGI) systems that can learn abstract and robust representations of objects, agents and the environment with minimal supervision, and achieve generalized human-level understanding.