Data-Driven Transfer of Insight Between Brains and AI Systems
To receive Zoom information, subscribe to the Stats seminar list.
Several major innovations in artificial intelligence (AI) (e.g. convolutional neural networks, experience replay) are based on findings about the brain. However, the underlying brain findings took many years to first consolidate and many more to transfer to AI. Moreover, these findings were made using invasive methods in non-human species. For cognitive functions that are uniquely human, such as natural language processing, there is no suitable model organism and a mechanistic understanding is that much farther away.
In this talk, I will discuss two works that circumvent these limitations by establishing a direct connection between the human brain and AI systems with two main goals: 1) to improve the generalization performance of AI systems and 2) to improve our mechanistic understanding of cognitive functions. Lastly, I will discuss future directions that build on these approaches to investigate the role of memory in meaning composition, both in the brain and AI. This investigation will lead to methods that can be applied to a wide range of AI domains, in which it is important to adapt to new data distributions, continually learn to perform new tasks, and learn from few samples
I'm a final-year PhD candidate at Carnegie Mellon in a joint program between Machine Learning and Neural Computation. I study how language is processed both by the brain and by machines. To get closer to this goal, I work with my advisors – Tom Mitchell and Leila Wehbe – to investigate the representations in the brain as subjects read naturalistic text in neuroimaging devices (both fMRI and Magnetoencephalography), as well as the representations of the same text as it is passed through current natural language processing models. My research is supported by the NSF graduate fellowship. Before beginning my graduate studies at CMU, I received a B.S. in both Computer Science and Cognitive Science at Yale University.