MODELING HUMAN LEARNING AND DEVELOPMENTAL DIFFERENCES

By building machines that learn more like people do, we hope to better understand how humans learn. To be more precise, we aim to build artificial systems that perform well at the challenging task of learning about the world by interacting with it, something we know that humans do well. We hypothesize that the behaviors (e.g. eye gaze, object grasping), neural activity, and capacities (e.g. ability to manipulate objects in skillful ways) of these artificial systems will reflect that in humans, from early childhood and throughout life.

Kim et al, "Towards modeling the developomental variability of human attention," 2020.

As an example, consider the task of deciding what to look at while interacting with others -- something that people must do every day, and in particular, something that children face constantly early in life. Childrens’ gaze behavior is, likely, an important part of developmental learning, as where we look affects what we can learn from others. Indeed, infant eye gaze behavior during this task is genetically driven [cite], and Autism Spectrum Disorder (ASD) children behave differently [cite cite cite].

This is but one facet of an emerging plethora of evidence suggesting that the capabilities we would like to give AI -- exploratory, interactive, and embodied learning -- are not only important for human development, but that they are different in children with learning differences. Understanding these differences on an algorithmic level will tell us a great deal more about how to characterize developmental differences and how to help those with them.

Kim et al, "Towards modeling the developomental variability of human attention," 2020.

  1. Kim, Kuno, Megumi Sano, Julian De Freitas, Daniel LK Yamins,* and Nick Haber.* Towards modeling the developmental variability of human attention. In Proceedings of the International Conference on Learning Representations Workshops, 2020. 

  2. Sano, Megumi, Julian De Freitas, Nick Haber,* and Daniel LK Yamins.* Learning in social environments with curious neural agents. In Proceedings of the 40th Annual Meeting of the Cognitive Science Society. 2020.

  3. Haber, Nick, Damian Mrowca, Li Fei-Fei, and Daniel LK Yamins. Emergence of structured behaviors from curiosity-based intrinsic motivation. In Proceedings of the 40th Annual Meeting of the Cognitive Science Society. 2018.

Stanford Graduate School of Education -Stanford Computer Science - 520 Galvez Mall - Stanford, CA 94305

©2020 by Autonomous Agents Lab. Created with Wix.com