In 1950, Alan Turing asked "Instead of trying to produce a programme to simulate the adult mind, why not rather try to produce one which simulates the child's?" Today, 75 years later, constructing a computer program that can learn like a child and that develops a human-like general intelligence and consciousness is still considered a grand, if not the ultimate, challenge for artificial intelligence (AI). An interdisciplinary community of scientists from AI, Cognitive Science, Psychology, Engineering, and Neuroscience are tackling this grand challenge. In the Developing Minds global lecture series we showcase the progress being made. It is organized by the Developmental AI Task Force of the IEEE Technical Committee on Cognitive and Developmental Systems of the IEEE Computational Intelligence Society. See also: IEEE Int. Conference on Development and Learning (ICDL), IEEE Transactions on Cognitive and Developmental Systems (TCDS).
Thursday, September 25, 2025
9:00 am EST (Eastern Standard Time, US)
14:00 UTC (Universal Coordinated Time)
15:00 CET (Central European Time)
22:00 JST (Japan Standard Time)
Uri Hasson
Princeton University, United States
"Developing cognitively feasible learning agents that can acquire language like children through real-life experiences"
Abstract
Understanding how humans learn to think, speak, and interact in natural environments is one of the most significant scientific challenges. Traditional computational models perform well in artificial tasks but struggle to generalize to real-life ecological situations. In contrast, new deep learning models excel at processing real-world information and demonstrate cognitive abilities close to those of humans. However, these models are trained on impractically large datasets and use training protocols that are not cognitively feasible, which limits their ability to explain or predict human learning and cognitive development. This project aims to develop the first cognitively feasible learning agents—AI systems that learn language and cognition within constraints that mimic human development. Leveraging a unique dataset (the 1kD corpus)— continuous daily audio-visual recordings from 18 children’s first 1,000 days of life—we will train models directly on the ecologically valid, socially embedded experiences that shape children’s growth. Unlike large-scale industrial models, which depend on vast impersonal datasets, our approach emphasizes individual-centered, real-world input that captures the long-tail variability of human development. By replicating learning trajectories across multiple households, we will establish the first mechanistic framework for how natural input shapes children’s cognition. The project represents a bold shift from analyzing existing models to building new brain-inspired learning agents, directly addressing ecological validity and laying the foundation for a new generation of cognitive science.
Short Bio
Uri Hasson grew up in Jerusalem. He studied philosophy and cognitive sciences at the Hebrew University as an undergrad. He completed his Ph.D. in Neurobiology at the Weizmann Institute in Israel and was a postdoctoral fellow at NYU before moving to Princeton. He is currently a Professor in the Psychology Department and the Neuroscience Institute at Princeton University. His research program aims to understand the neural basis of face-to-face, brain-to-brain, communication in real-world contexts, using big ECoG data and deep language models.
Please sign up here to receive access information and announcements of future talks. The login credentials for the talk will be contained in the welcome message you receive after subscribing to the email list.
2025-09-25: Uri Hasson, Princeton University, United States
2025-10-16: Denis Mareschal, Birkbeck College, University of London, UK
2025-11-13(?): Tadahiro Taniguchi, Kyoto University, Japan
2024-12-12: Daniel Messinger, "Does Interaction Drive Development? Lessons from infant emotion, autism, and preschool language". Video
2024-11-12: Justin N. Wood, "Radical empiricism: The origins of knowledge as a mini-evolution". Video
2024-04-18: Sabine Hunnius, "Early cognitive development: Five lessons from infant learning". Video
2024-01-24: Caroline Rowland, "What predicts how quickly children learn language?" Video
2023-11-30: Brenden Lake, "Addressing two classic debates in cognitive science with deep learning". Video
2023-06-28: Angelo Cangelosi, "Developmental Robotics for Language Learning, Trust and Theory of Mind". Video
2023-04-27: Karl Friston, "Active Inference and Artificial Curiosity". Video
2023-03-02: Masashi Sugiyama, "Theory and Algorithm towards Reliable Machine Learning". Video
2022-12-08: Karen E. Adolph, "Development of intelligent behavior: Lessons from Infants". Video
2022-11-17: Gary Marcus, "Towards a Proper Foundation for Robust Artificial Intelligence". Video
2022-07-28: Sergey Levine, UC Berkeley, "From Reinforcement Learning to Embodied Learning". Video
2022-06-01: Susan Goldin-Meadow, U. of Chicago, "The Mind Hidden in Our Hands". Video
2022-03-31 : Atsushi Iriki, Riken, "Self-in-the-world map evolved in the primate brain as a basis of civilized Homo sapiens". Video
2022-01-27: Josh Tenenbaum, MIT, "Reverse Engineering Human Cognitive Development: What do we start with, and how do we learn the rest?". Video
2021-11-11: Linda B. Smith, Indiana University, "Babies, bodies, brains and machines". Video
2021-09-30: Pierre-Yves Oudeyer, INRIA, "Developmental Artificial Intelligence: machines that learn like children and help children learn better". Video
If you like our talks, also check out the keynote lectures from the 2022 ICDL conference!