Events

DMS Statistics and Data Science Seminar

Time: Apr 07, 2022 (02:00 PM)
Location: 228 Parker Hall

Details:

Speaker: Luke Oeding (local)

Title: What do Tensors and Geometry have to do with Deep Neural Networks?

Abstract: At a basic level Deep Neural Networks (DNNs) are frameworks for representing functions. The network architecture (number of layers, and widths of layers) and design choices (types of activation functions at nodes) determine the complexity (expressive power) of function that can be represented by that network. From linear interpolation to Multilinear Algebra, the geometry of tensors play an important role in understanding the expressive power of DNNs. I’ll explain this connection, and describe some open questions. I hope to make the talk very basic as it is about proposed research.