The IACS seminar series is free and open to the public but registration is required.
Talk Abstract: Activity patterns of neural populations in natural and artificial neural networks constitute representations of data. The nature of these representations and how they are learned are key questions in neuroscience and deep learning. In his talk, Professor Pehlevan will describe his group’s efforts in building a theory of representations as feature maps leading to sample efficient function approximation. Kernel methods are at the heart of these developments. He will present applications of his group's theories to deep learning and neuronal data.
Speaker Bio: Cengiz Pehlevan is Assistant Professor of Applied Mathematics at the Harvard John A. Paulson School of Engineering and Applied Sciences. He is working towards uncovering the brain’s algorithms and their biological implementation. He explores applications of these algorithms to machine learning problems. In his research, Pehlevan uses mathematical techniques from a wide range of disciplines, including statistics, engineering and physics. He works in close collaboration with experimentalists. Pehlevan holds a doctorate in physics from Brown University. He was a Swartz Fellow at Harvard University and a postdoctoral associate at Janelia Research Campus. Prior to joining SEAS, Pehlevan was a research scientist at the Flatiron Institute.