Powered by Indico v3.0.3
Abstract:
Machine learning technique has been widely used in high energy physics, most applications are focus on reconstruction and data analysis. Simulation data plays a crucial role in algorithm development and aids in comprehending experimental data. However, the production of simulation data often necessitates substantial computing resources, posing a bottleneck in generating large-scale statistically significant simulations. Furthermore, simulations may exhibit inaccuracies and discrepancies when compared to experimental data, giving rise to the challenge of domain shift. Fortunately, machine learning techniques offer promising solutions to these issues. This presentation aims to share some applications of machine learning in simulation, aiming to achieve faster and more accurate simulations.
About the speaker:
Wenxing Fang graduated with a bachelor’s degree from the School of Physics at Beihang University in 2014, and with a joint Ph.D from Beihang University and Université libre de Bruxelles in 2019. Afterwards, he held a postdoctoral position at Institute of High Energy Physics for two years. He joined Institute of High Energy Physics in 2021. Currently, he is an assistant researcher at Experimental Physics Division. He has been involved in collider experiment and neutrino experiment. He is currently a member of the BESIII and JUNO collaborations, focusing on the offline software development and machine learning.
-------------------------------------
Meeting ID 会议号: 92121645917
Meeting URL 会议链接:: https://zoom.us/j/92121645917?pwd=azZ4QmNSVU1Xa0x2VFoybFFhd1FMdz09
HostKey 主持人密钥: 740212
Password 会议密码: 240522