Mapping Dark Matter with Bayesian Neural Networks with Yashar Hezaveh

Today we're joined by Yashar Hezaveh, Assistant Professor at the University of Montreal, and Research Fellow at the Center for Computational Astrophysics at Flatiron Institute. Yashar and I caught up to discuss his work on gravitational lensing, which is the bending of light from distant sources due to the effects of gravity. In our conversation, Yashar and I discuss how machine learning can be applied to undistort images, including some of the various techniques used and how the data is prepared to get the best results. We also discuss the intertwined roles of simulation and machine learning in generating images, incorporating other techniques such as domain transfer or GANs, and how he assesses the results of this project. You might have seen the news yesterday that MIT researcher Katie Bouman produced the first image of a black hole. What's been less reported is that the algorithm she developed to accomplish this is based on machine learning. Machine learning is having a huge impact in the fields of astronomy and astrophysics, and I'm excited to bring you interviews with some of the people innovating in this area. For even more on this topic, I'd also suggest checking out the following interviews, TWIML Talk #117 with Chris Shallue, where we discuss the discovery of exoplanets, TWIML Talk #184, with Viviana Acquaviva, where we explore dark energy and star formation, and if you want to go way back, TWIML Talk #5 with Joshua Bloom which provides a great overview of the application of ML in astronomy.