WaveFormer: transformer-based denoising method for gravitational-wave data

中国物理学会引力与相对论天体物理分会“2024年学术年会”暨第六届伽利略-徐光启国际会议

Frontiers of AI in Gravitational Wave Astronomy: From Data Processing to Scientific Discovery

第二届天文大数据与人工智能研讨会(2024)

Frontiers of AI in Gravitational Wave Astronomy

第一届音频波段引力波天文学前沿学术研讨会(2024)

空间引力波科学数据处理的挑战与人工智能技术应用 (16:9)

第五届全球京师青年学者论坛-天文学科分论坛

结营仪式与课程总结（后记）

引力波数据探索：编程与分析实战训练营。课程网址：https://github.com/iphysresearch/GWData-Bootcamp

第 4 部分 深度学习基础（卷积神经网络与引力波信号探测）

引力波数据探索：编程与分析实战训练营。课程网址：https://github.com/iphysresearch/GWData-Bootcamp

第 4 部分 深度学习基础（深度学习技术概述与神经网络基础）

引力波数据探索：编程与分析实战训练营。课程网址：https://github.com/iphysresearch/GWData-Bootcamp

第 3 部分 机器学习基础（机器学习算法之应用进阶）

引力波数据探索：编程与分析实战训练营。课程网址：https://github.com/iphysresearch/GWData-Bootcamp

第 3 部分 机器学习基础（机器学习算法之应用起步）

引力波数据探索：编程与分析实战训练营。课程网址：https://github.com/iphysresearch/GWData-Bootcamp

第 2 部分 基于 Python 的数据分析基础（数据分析可视化之 Matplotlib / Seaborn）

引力波数据探索：编程与分析实战训练营。课程网址：https://github.com/iphysresearch/GWData-Bootcamp

第 2 部分 基于 Python 的数据分析基础（数据分析实训之 Pandas）

引力波数据探索：编程与分析实战训练营。课程网址：https://github.com/iphysresearch/GWData-Bootcamp

第 2 部分 基于 Python 的数据分析基础（数据分析实训之 Numpy）

引力波数据探索：编程与分析实战训练营。课程网址：https://github.com/iphysresearch/GWData-Bootcamp

第 2 部分 基于 Python 的数据分析基础（数据科学语言 Python 入门到熟悉）

引力波数据探索：编程与分析实战训练营。课程网址：https://github.com/iphysresearch/GWData-Bootcamp

第 1 部分 编程开发环境与工作流 (Git分布式版本控制系统)

引力波数据探索：编程与分析实战训练营。课程网址：https://github.com/iphysresearch/GWData-Bootcamp

第 1 部分 编程开发环境与工作流 (Linux运维基础与Docker容器化技术)

引力波数据探索：编程与分析实战训练营。课程网址：https://github.com/iphysresearch/GWData-Bootcamp

第 0 部分 课程介绍会 (通向自我实现之路)

引力波数据探索：编程与分析实战训练营。课程网址：https://github.com/iphysresearch/GWData-Bootcamp

Gravitational Wave Detection and AI Technology: New Methods for Unveiling the Mysteries of the Universe

Nov. 7, 2023, 17:05-17:20. International Workshop on Intelligent Computing in Astronomy "Computing Senses Cosmos" (2023) @Zhejiang Lab, Hangzhou, China

空间引力波科学数据处理的挑战与人工智能技术应用 (16:9)

2023年“第三届空间科学大会”空间引力波探测和精密测量与引力宇宙 | 浙江·德清 https://cssr.kejie.org.cn/meeting/cssa2023/

引力波探测与AI技术：揭示宇宙奥秘的新手段

2023年“第二届机器学习在天文学中的应用”研讨会 | 湖北·宜昌 https://machinelearning2023.casconf.cn/

针对引力波观测数据的智能噪声抑制

2023 中国物理学会秋季学术会议 | 中国·银川

@TianQin GWML Tutorial 3

He Wang. (2023). Can you find the GW signals?. Kaggle. https://kaggle.com/competitions/can-you-find-the-gw-signals. (引力波暑期学校 Summer School on Gravitational Waves) [Repo: https://github.com/iphysresearch/2023gwml4tianqin]

@TianQin GWML Tutorial 2

He Wang. (2023). Can you find the GW signals?. Kaggle. https://kaggle.com/competitions/can-you-find-the-gw-signals. (引力波暑期学校 Summer School on Gravitational Waves) [Repo: https://github.com/iphysresearch/2023gwml4tianqin]

@TianQin GWML Tutorial 1

He Wang. (2023). Can you find the GW signals?. Kaggle. https://kaggle.com/competitions/can-you-find-the-gw-signals. (引力波暑期学校 Summer School on Gravitational Waves) [Repo: https://github.com/iphysresearch/2023gwml4tianqin]

UCAS-SummerSchool

引力波探测与AI技术：揭示宇宙奥秘的新手段

The detection of gravitational waves has revolutionized our understanding of the universe and has opened new doors to the cosmos. However, the data generated by these detections are often noisy and difficult to analyze. In recent years, the application of AI technology, particularly deep learning, has shown great potential in the field of gravitational wave detection and analysis. In this talk, we will explore the use of AI in gravitational wave detection and discuss how it has enabled us to unveil new mysteries of the universe. We will highlight the challenges and opportunities of this interdisciplinary field and discuss the role of AI in advancing our understanding of the cosmos. The talk will cover topics such as the application of AI in signal processing, gravitational wave denoising, and machine learning for gravitational wave data analysis. We will also discuss future directions and the potential impact of AI on cosmology and astrophysics research.

机器学习在引力波数据分析中的应用——参数估计及数据降噪

引力波数据分析系列报告 | 时间:2023年6月11日(周日)下午14:00 | 中国科学院力学研究所怀柔园区1号楼430会议室

AI For Science 创客松——人工智能驱动的科学研究

北京·朝阳·大望路·郎园 Vintage OurTimesHere 复合型共享空间(果壳;首创郎园 AIGC 创业产业基地)。 6 月 3 日 13:30-18:30 入场时间:13:00。

Clearing the Path to Discovery: Detecting and Denoising Gravitational Waves with Deep Learning

中国物理学会引力与相对论天体物理分会“2023年学术年会” 2023.04.23 11:10-11:30 | 中国·重庆

基于人工智能技术的引力波数据分析前沿

天文信息学与虚拟天文台2022年学术年会，2022 年 4 月 20 日 15:45-16:00 | 会场LED屏显示比例为16:9

基于引力波探测开源数据的共享数据门户

国家天文科学数据中心 · 青年数据科学家项目交流会议

机器学习在引力波数据处理中的应用

东北大学引力波宇宙学与射电天文学研究中心青年学者研讨会 - 特邀报告 (2022.12.21)

机器学习在引力波数据处理中的应用

Taiji Seminar (2022.10.31) Poster: https://ictp-ap.org/event/60

Deep neural networks and GW signal recognization

ML session of a semester at TsingHua Univ. 2022.07.04

Exploring Gravitational-Wave Detection & Parameter Inference using Deep Learning

中国物理学会引力与相对论天体物理分会 · 2022 年学术年会 (Domestic Session)

Exploring Gravitational-Wave Detection and Parameter Inference using Deep Learning

The 2022 ITP Postdoctoral Symposium

Exploring Gravitational-Wave Detection and Parameter Inference using Deep Learning

The 8th KAGRA International Workshop , 14:30-14:45 KST on July 9th, 2021

Gravitational-wave Signal Recognition of LIGO Data by Deep Learning

中国物理学会引力与相对论天体物理分会 , 14:40-15:00 on April 24th, 2021

Statistical inference with normalized flow for BBHs in O1/O2

We reproduced a same state-of-the-art result (Green et al. 2008.03312) for GW150914 and applied the formulism to the other GW events. Normalized flow model and how we pre-rocessing the data will be explained by pedagogy. (omitted) Some on-going works are also mentioned. I have to explain this in Chinese for clarity...🙏

Particle Swarm Optimization From Scratch Using Python

https://github.com/iphysresearch/PSO_python_demo/

Statistical learning inference in GW astronomy

Abtract: 1. An introduction on model selection of Bayesian inference in GW astronomy (Ref: 1809.02293, book:「Pattern Recognition and Machine Learning」)；2. What is KS test and how to plot p-p plot (Ref: 1409.7215)；3. (optional) Recent progress of normalized flow in GW data analysis (Ref: 2002.07656/2008.03312 et al.).

Gravitational-wave Signal Recognition of LIGO Data by Deep Learning

7th KAGRA International Workshop , 15:45-16:05 Asia/Taipei on December 19\(^\text{th}\), 2020

Gravitational-wave Signal Recognition of LIGO Data by Deep Learning

The 26th KAGRA Face-to-Face meeting, 13:30-14:30 JST on December 17th^\text{th}th, 2020

Matched-filtering Techniques & Deep Neural Networks

Apache MXNet Day, 10:01 AM PST on December 14th, 2020

Signal Processing

Building a deep neural network and How could we use it as a density estimator

Abstract: Firstly, I will talk about some basic concepts of deep neural networks and I hope it would help clear up misunderstandings and rumors related to understand how a neural network works, etc. Then, based on these concepts, I will try to briefly review the current GW ML parameter estimation studies (1903.01998, 1909.06296, PRL(2020) 124 041102, 2002.07656, 2008.03312; selected), especially how they try to built up a neural network to estimate the posterior distribution. The relative drawbacks and mysteries of their works are also mentioned.

Deep neural networks and GW signal recognization

ITP-CAS, Webniar, Aug 13rd, 2020

Matched-filtering & Deep Learning Networks

Webniar

PhD defense slides

引力波探测中关于深度学习数据分析的研究

Slide_UCAS

https://gdlab.ucas.ac.cn/index.php/zh-CN/xsbg-2/2907-2020-01-08-00-47-20 (Jan 10th, 2020)

GWHM & 2-OGC

2019.10.16 的组会