Geordie Williamson - What can the working mathematician expect from deep learning? - IPAM at UCLA

Recorded 13 February 2023. Geordie Williamson of the University of Sydney presents "What can the working mathematician expect from deep learning?" at IPAM's Machine Assisted Proofs Workshop. Abstract: Deep learning (the training of deep neural nets) is a simple idea, which has had many extraordinary applications throughout industry and science over the last decade. In mathematics the impact has so-far been modest at best. I will discuss a few instances where it has proved useful, and led to interesting (pure) mathematics. I will also discuss what can be learned from these examples, and try to guess an answer to the question in the title. I will also reflect on my experience as a pure mathematician interacting with deep learning. Learn more online at: http://www.ipam.ucla.edu/programs/wor...