The seminar begins at 12:00 p.m. Refreshments will be available starting at 1:15 p.m.
Abstract
There is an enormous data gap between how AI systems and children learn language: The best LLMs now learn language from text with a word count in the trillions, whereas it would take a child roughly 100K years to reach those numbers through speech. There is also a clear generalization gap: Whereas machines struggle with systematic generalization, people excel. For instance, once a child learns how to “skip,” they immediately know how to “skip twice” or “skip around the room with their hands up” due to their compositional skills. In this talk, Brenden Lake will describe two case studies in addressing these gaps.
The first addresses the data gap, in which deep neural networks were trained from scratch, not on large-scale data from the web, but through the eyes and ears of a single child. Using head-mounted video recordings from a child, this study shows how deep neural networks can acquire many word-referent mappings, generalize to novel visual referents, and achieve multi-modal alignment. The results demonstrate how today’s AI models are capable of learning key aspects of children’s early knowledge from realistic input.
The second case study addresses the generalization gap. Can neural networks capture human-like systematic generalization? This study addresses a 35-year-old debate catalyzed by Fodor and Pylyshyn’s classic article, which argued that standard neural networks are not viable models of the mind because they lack systematic compositionality—the algebraic ability to understand and produce novel combinations from known components. This study shows how neural networks can achieve humanlike systematic generalization when trained through meta-learning for compositionality (MLC), a new method for optimizing the compositional skills of neural networks through practice. With MLC, a neural network can match human performance and solve several machine learning benchmarks.
Given this work, we’ll discuss the paths forward for building machines that learn, generalize, and interact in more humanlike ways based on more natural input.
Speaker Biography
Brenden M. Lake is an assistant professor of psychology and data science at New York University. He received his MS and BS in symbolic systems from Stanford University in 2009 and his PhD in cognitive science from the Massachusetts Institute of Technology in 2014. Lake was a postdoctoral data science fellow at NYU from 2014–2017. He is a recipient of the Robert J. Glushko Prize for Outstanding Doctoral Dissertation in Cognitive Science, he was named an Innovator Under 35 by MIT Technology Review, and his research was selected by Scientific American as one of the 10 most important advances of 2016. Lake’s research focuses on computational problems that are easier for people than they are for machines, such as learning new concepts, creating new concepts, learning to learn, and asking questions.