报告题目：Deep Learning for black hole image generation and cosmological parameter estimation
报 告 人：Prof. 王接词（湖南师范大学）
报告时间：2025年10月9日（周四）下午14:30
报告地点：物理科学与技术学院新楼D-503多功能厅
报告摘要：
Deep Learning has emerged as a powerful tool for addressing complex scientific challenges, particularly in the domains of image generation, parameter estimation, and large-scale data analysis within gravitational theory and cosmological research. Meanwhile, extracting information about the universe directly from observational and simulated datasets, without relying on prior assumptions, has become increasingly significant. In this presentation, I will provide an overview of our group's recent advancements in applying novel deep learning methodologies for generating black hole images and estimating cosmological parameters. Specifically, I will discuss our work on black hole image generation using the Branch-Corrected Denoising Diffusion Model. Furthermore, I will present our research on improving cosmological parameter estimation through Long Short-Term Memory Networks, as well as the reconstruction of Hubble parameter based on the Ef-KAN model.
报告人简介：
王接词，湖南师范大学教授、博士生导师。主要研究方向是引力和相对论性量子信息理论。在Physics Reports、Physical Review Letters, Nature Communications, ApJS/ApJL等期刊发表论文90余篇，单篇最高他引550余次。主持了国家自然科学基金优秀青年科学基金项目、面上项目、湖南省杰出青年科学基金项目等研究项目11项，同时参与了国家自然科学基金创新群体项目、重点项目等多个团队项目。入选了湖南省“科技创新领军人才”、“湖湘青年英才”和 “121创新人才培养工程”等人才计划，获“国家优秀自费留学生”等奖励。担任湖南省物理学会副秘书长、《Sci. China-Phys. Mech. & Astron.》青年编委、《Scientific Reports》编委、《Frontiers of Physics》青年编委。
邀 请 人：范锡龙 教授
