From: 王赫 <[email protected]> Date: Sunday, November 8, 2020 at 11:03 PM To: apachemxnetday <[email protected]> Subject: Re: Presentation Requested for Apache MXNet Day
I would like to give a presentation on my recent work. It relates on category of "research and applications" for Apache MXNet. Title: Matched-filtering Techniques and Deep Neural Networks —— Application for Gravitational Wave Astronomy Abstract: Deep learning is a neural-inspired pattern recognition technique that has been shown to be as effective as conventional signal processing. And It has been shown have considerable potential to identify gravitational-wave (GW) signals in highly noisy data. In this talk, I will first review some related works on the detection and characterization of GW signals and some fundamental background of GW data. I will then present our recent paper (DOI: 10.1103/physrevd.101.104003<https://journals.aps.org/prd/abstract/10.1103/PhysRevD.101.104003>) about the effect of matched-filtering convolutional neural networks (MFCNN) we proposed on the GW recognition and identifying generalization properties of gravitational waves. Powered by MXNet, a brand-new network architecture is presented. At last, some insights on the model are presented. He Wang ------------------------------------------------------------- He WANG (王赫), Postdoc at ITP-CAS, Ph.D. from BNU. Member of KAGRA collaboration. Phone: +86 188 1155 7200 Email: [email protected]<mailto:[email protected]>/ [email protected]<mailto:[email protected]> My Site: https://iphysresearch.github.io/ -------------------------------------------------------------
