CSIG-VIS International Lecture Series 9
    Prof. Koji KOYAMADA | Visual analysis to support the derivation and solution of PDEs using neural networks


    Speaker: Prof. Koji KOYAMADA

    Kyoto University, Japan.

    Topic: Visual analysis to support the derivation and solution of PDEs using neural networks

    Time: Jan.20, 2022 19:00-20:30 (China Standard Time)

    Abstract: This paper proposes a visual analysis (VA) approach to support the high-precision derivation and solution of PDEs from point cloud data using neural networks (NN). Point cloud data consists of spatiotemporal coordinates in which the data is defined and physical data associated with those coordinates. In NN, spatiotemporal coordinates are input, physical data is output, and a function that approximates point cloud data is regressed. As a result, especially when solving the equation, the residual of the partial differential equation becomes a loss function. Also, although optimization of the NN structure is important, it is difficult to automate and it is mainly left to the user. Therefore, when deriving and solving PDEs from point cloud data, we will develop a VA that emphasizes the importance of human involvement in parallel with the process of automatically constructing the NN model. VA consists of advanced visualization technologies in space-time and parameter space, and the loss function in NN. To confirm the effectiveness of the method, we will clarify the requirements to support the derivation and solution of PDEs by experts.

    Speaker Bio: Prof. Koji Koyamada is currently a professor at the Academic Center for Computing and Media Studies, Kyoto University, Japan. His research interest includes modeling & simulation and visualization. He is a member of the Science Council of Japan, a former president of the Visualization Society Japan, and a former president of Japan Society of Simulation Technology. He received the IEMT/IMC outstanding paper award in 1998, the VSJ contribution award in 2009 and the VSJ outstanding paper award in 2010. He received his B.S., M.S. and Ph.D. degrees in electronic engineering from Kyoto University, Japan in 1983, 1985 and 1994, respectively, and worked for IBM Japan from 1985 to 1998. From 1998 to 2001 he was an associate professor at the Iwate Prefectural University, Japan. From 2001 to 2003, he was an associate professor at Kyoto University, Japan

    Live Stream： http://live.bilibili.com/24003948

    qrcode



    Session Chair: Yadong Wu

    Sichuan University of Science & Engineering

    Session Chair Bio: Wu Yadong, professor and doctoral advisor of Sichuan University of Science & Engineering, President of School of computing science and engineering, executive vice president of high-tech industry integration development research institute, executive vice director of Sichuan big data visual analysis technology engineering laboratory, and head of Sichuan big data visual innovation team. He is mainly engaged in the field of visualization and human-computer interaction. Deputy Secretary General of CSIG Special Committee on visualization and visual analysis and former president of chinavis Conference (2019 and 2020). Outstanding member of CCF, chairman of CCF YOCSEF Chengdu, chairman of CCF Mianyang.







    About Us

    Webpage: http://chinavis.org/lectures/english/index_en.html
    Email：csig_vis_forum@163.com

    About CSIG-VIS

    The China Society of Image and Graphics, Technical Committee on Visualization and Visual Analytics (CSIG-VIS) is the first technical committee on visualization and visual analytics in China. The technical committee aims to develop a communication platform for stakeholders in academia and industry, to discuss the trends and opportunities in the era of big data, to promote the discipline development and talent cultivation, to push forward the research and applications in the related disciplines, and ultimately to build a sustainable ecosystem involving industry, universities, and other research institutes. The technical committee, officially established on December 23, 2017, already attracts more than 100 members from various affiliations, including domestic and international universities and companies.

    About The CSIG-VIS International Lecture Series

    The CSIG-VIS International Lecture Series, launched by the China Society of Image and Graphics, Technical Committee on Visualization and Visual Analytics, invites renowned experts to share their visions of the research trends and latest progress in visualization. These biweekly lectures are conducted in Thursday, and please refer to http://chinavis.org /lectures/english/index_en.html for details.