We are glad to have Daniel George, as our speaker for this week’s social hour on Friday, March 3 at 3:00PM in 369 CSL. This session is titled as “Deep learning for extracting signals weaker than noise: Detecting gravitational waves”.
Bio: Daniel George is a PhD student in Astronomy, pursuing the Computational Science and Engineering concentration, at the University of Illinois at Urbana-Champaign. He obtained his Bachelor’s degree in Engineering Physics from IIT Bombay. He is currently a Research Assistant in the Gravity Group at the National Center for Supercomputing Applications (NCSA) and a member of the LIGO collaboration working at the interface of deep learning, high-performance computing, and gravitational wave astrophysics. His long-term interests lie in applying cutting-edge computer science and technology, especially artificial intelligence, to accelerate discoveries in the fundamental sciences.
Abstract: Daniel will describe a new technique which can rapidly extract weak signals with signal-to-noise ratio (SNR) as low as 0.25. This outperforms matched-filtering and other machine learning methods. It also extends the range of gravitational waves that can be detected by LIGO, thus enabling immediate follow-up campaigns. Furthermore, the same technique can detect and classify transients from raw telescope data. This initiates a new paradigm for research which uses massively-parallel simulations to train artificial intelligence algorithms that exploit emerging hardware architectures.