Geometry, AI and the Brain

A large body of experiments suggests that neural computations reflect, in some sense, the world’s geometry. Such results pose unanswered questions. How do artificial and neural systems learn representations of the world that reflect its geometry? How do we, as humans, learn representations of objects — such as fruits — that reflect the geometry of object space? Developing artificial systems that can capture and understand the geometry of the data they process may enable them to learn representations useful in many different contexts and tasks.

In this talk, Demba Ba will describe an artificial neural-network architecture based on a simple union-of-manifold model of data comprising objects from different categories. This architecture mimics aspects of how primates learn, organize and retrieve concepts in a manner that respects the geometry of object space.

To attend this in-person event, you will need to:
• Be aged 18 or older
• Register in advance
• Provide valid photo ID upon entering the building
• Present your digital or printed Eventbrite ticket confirmation; make sure it is for the correct event and that the name on it matches your ID
• Wear a mask while in the auditorium and restrooms

Please note that by entering the Simons Foundation, you are attesting that you are not experiencing COVID symptoms and are not knowingly positive for COVID.