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.
Speaker Bio:
Ba is an associate professor of electrical engineering and bioengineering in Harvard University’s School of Engineering and Applied Sciences, where he directs the CRISP group. Recently, he has taken a keen interest in the connection between artificial neural networks and sparse signal processing. His group leverages this connection to solve data-driven unsupervised learning problems in neuroscience to understand the principles of hierarchical representations of sensory signals in the brain and develop explainable AI. In 2016, he received a research fellowship in neuroscience from the Alfred P. Sloan Foundation. In 2021, Harvard’s Faculty of Arts and Sciences awarded him the Roslyn Abramson Award for outstanding undergraduate teaching.
