It is hard to imagine our modern life without machine learning: AI algorithms help us navigate complex patterns of traffic and financial markets, diagnose medical problems, eliminate biases in judgment, and assist with many other complex tasks. Neural nets have been extensively used in data-intensive branches of experimental and observational sciences. In this talk, intended for a broad audience, I will illustrate how machine learning can also help with paper-and-pencil type derivations in purely theoretical branches. Initially, it starts as two parallel stories, one about the cutting-edge algorithms in machine translation and the other involving questions that until recently were only approached via abstract mathematical methods. The confluence of the two then leads to unexpected results and opens new doors for future research in theoretical and mathematical sciences.
Must have valid Caltech ID to attend in person.
Feynman Lecture Hall, 201 E. Bridge Laboratory
Join via Zoom: https://caltech.zoom.us/j/89237465190. Meeting ID: 892 3746 5190