Modeling Human Learning and Developmental Differences
We seek to create computational models of human learning and development, and in particular, models of developmental differences such as Autism Spectrum Disorder. To do this, we engineer artificial systems that learn as humans do, in complex, real-world situations, and we compare artificial behavior to human behavior.
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.
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.
Children exhibit extraordinary exploratory behaviors hypothesized to contribute to the building of models of their world. Harnessing this capacity in artificial systems promises not only more flexible technology but also cognitive models of the developmental processes we seek to mimic. Yet not all children learn the same way, and for instance children with autism exhibit characteristically different exploratory strategies early in life. What if we could, by developing artificial systems that learn through exploration, model not only typically development, but all its variations? In this work, we present a preliminary analysis of curiosity-driven agents in social environments that establishes links between early behavior and later acuity, with implications for the future of both diagnostics and personalized learning.
@article{kim_towards_2020,author={Kim, Kuno and Sano, Megumi and Freitas, Julian De and Yamins, Daniel LK and Haber, Nick},citation={},year={2020},title={TOWARDS MODELING THE DEVELOPMENTAL VARIABIL-ITY OF HUMAN ATTENTION},_google_scholar_id={YOwf2qJgpHMC},}
Learning in social environments with curious neural agents
Megumi Sano, Julian De Freitas, Nick Haber, and 1 more author
Proceedings of the Annual Meeting of the Cognitive Science Society, 2020
From an early age, humans are capable of learning about theirsocial environment, making predictions of how other agentswill operate and decisions about how they themselves will in-teract. In this work, we address the problem of formalizing thelearning principles underlying these abilities. We construct a cu-rious neural agent that can efficiently learn predictive models ofsocial environments that are rich with external agents inspiredby real-world animate behaviors such as peekaboo, chasing,and mimicry. Our curious neural agent consists of a controllerdriven by -Progress, a scalable and effective curiosity signal,and a disentangled world model that allocates separate networksfor interdependent components of the world. We show that ourdisentangled curiosity-driven agent achieves higher learning ef-ficiency and prediction performance than strong baselines. Cru-cially, we find that a preference for animate attention emergesnaturally in our model, and is a key driver of performance. Fi-nally we discuss future directions including applications of ourframework to modeling human behavior and designing earlyindicators for developmental variability.
@article{sano_learning_2020,author={Sano, Megumi and Freitas, Julian De and Haber, Nick and Yamins, Daniel LK},citation={Proceedings of the Annual Meeting of the Cognitive Science Society 42, 2020},journal={Proceedings of the Annual Meeting of the Cognitive Science Society},year={2020},title={Learning in social environments with curious neural agents},volume={42},_google_scholar_id={ZeXyd9-uunAC},}
2018
Emergence of structured behaviors from curiosity-based intrinsic motivation
Nick Haber, Damian Mrowca, Li Fei-Fei, and 1 more author
Infants are experts at playing, with an amazing ability to generate novel structured behaviors in unstructured environments that lack clear extrinsic reward signals. We seek to replicate some of these abilities with a neural network that implements curiosity-driven intrinsic motivation. Using a simple but ecologically naturalistic simulated environment in which the agent can move and interact with objects it sees, the agent learns a world model predicting the dynamic consequences of its actions. Simultaneously, the agent learns to take actions that adversarially challenge the developing world model, pushing the agent to explore novel and informative interactions with its environment. We demonstrate that this policy leads to the self-supervised emergence of a spectrum of complex behaviors, including ego motion prediction, object attention, and object gathering. Moreover, the world model that the agent learns supports improved performance on object dynamics prediction and localization tasks. Our results are a proof-of-principle that computational models of intrinsic motivation might account for key features of developmental visuomotor learning in infants.
@article{haber_emergence_2018,author={Haber, Nick and Mrowca, Damian and Fei-Fei, Li and Yamins, Daniel LK},citation={arXiv preprint arXiv:1802.07461, 2018},journal={arXiv preprint arXiv:1802.07461},year={2018},title={Emergence of structured behaviors from curiosity-based intrinsic motivation},_google_scholar_id={aqlVkmm33-oC},}
