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.
Subscribe: iTunes / Google Play / Spotify / RSS
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.
Join me at Pegaworld!
We’d like to join Pegasystems, who is sponsoring today’s episode, in inviting you to meet meat the MGM Grand in Las Vegas June 2nd-5th at PegaWorld, the company’s annual digital transformation conference.
Pegasystems puts AI at the center of its customer engagement software so that it optimizes every customer touchpoint on every channel in real time. That way each interaction is relevant and timely to each individual customer, no matter if it’s a sales call, a digital marketing campaign or a customer service chat either online or in-store, and the system always learning in real-time to make the next interaction better.
Pegas customers are the real stars at PegaWorld. There you’ll hear great stories of AI applied to the customer experience at real Pega customers. The event is a great way to learn from a who’s who of the Fortune 500, and of course, I’ll be there and speaking as well.
To register, visit pegaworld.com and use the promo code TWIML19 when you sign up for $200 off. Again that’s TWIML19. It’s as easy at that. Hope to see you there!
Mentioned in the Interview
- Paper: Fast automated analysis of strong gravitational lenses with convolutional neural networks
- Paper: Uncertainties in Parameters Estimated with Neural Networks: Application to Strong Gravitational Lensing
- Paper: Analyzing interferometric observations of strong gravitational lenses with recurrent and convolutional neural networks
- Paper: Data-Driven Reconstruction of Gravitationally Lensed Galaxies using Recurrent Inference Machines
- Writeup: Neural networks meet space
- Check out all of our great series from 2018 at the TWiML Presents: Series page!
- TWiML Online Meetup
- Register for the TWiML Newsletter
“More On That Later” by Lee Rosevere licensed under CC By 4.0