
Prof. Dr.
Jochen Triesch
Frankfurt Institute of Advanced Studies
Neuroscience
Ruth-Moufang-Straße 1
60438 Frankfurt am Main
Short info
My goal is to better understand how brains can learn so much more autonomously than current AI systems and how we can mimic this ability in future AIs. Taking inspiration from the cognitive development of infants and children, we are constructing computational models of human learning processes and let AIs grow up and learn in simulated physical environments. We see this „Developmental AI” as a promising route towards a more human-like general intelligence. Next to this basic research, we are also developing new machine learning techniques to help us better understand brain data, in particular in the context of brain disorders.
Articles
Toddler-inspired embodied vision for learning object representations.
IEEE Int. Conf. on Development and Learning (ICDL).
MIMo: A Multi-Modal Infant Model for Studying Cognitive Development in Humans and AIs.
IEEE Int. Conf. on Development and Learning (ICDL), accepted.
Contrastive Learning Through Time.
In SVRHM 2021 Workshop@ NeurIPS.