CSIG-VIS International Lecture Series 26
Prof. Alexandru Telea | Visualizing the black box of machine learning: Challenges and opportunities


Speaker: Prof. Alexandru Telea

Utrecht University

Topic: Visualizing the black box of machine learning: Challenges and opportunities

Time: March 2,2023 19:00-20:30 Beijing time (UTC/GMT+08:00)

Abstract: Machine learning (Ml) has witnessed tremendous successes in the last decade in classification, regression, and prediction tasks. However, many ML models are used, and sometimes even designed, as black boxes. When such models do not operate properly, their creators do not often know what is the best way to improve them. Moreover, even when operating successfully, users often require to understand how and why they take certain decisions to gain trust therein. We present how information visualization and visual analytics help towards explaining (and improving) ML models. These cover tasks such as understanding high-dimensional datasets; understanding unit specialization during the training of deep learning models; exploring how training samples determine the shape of classification decision boundaries; and helping users annotating samples in semi-supervised active learning scenarios.

Speaker Bio: Alexandru Telea is a Professor of Visual Data Analytics at the Department of Information and Computing Sciences, Utrecht University. He holds a PhD from Eindhoven University and has been active in the visualization field for over 22 years. He has been the program co-chair, general chair, or steering committee member of several conferences and workshops in visualization, including EuroVis, VISSOFT, SoftVis, and EGPGV. His main research interests cover unifying information visualization and scientific visualization, high-dimensional visualization, and visual analytics for machine learning. He is the author of the textbook "Data Visualization: Principles and Practice" (CRC Press,2014).
https://webspace.science.uu.nl/~telea001/Main/HomePage

Live Stream： https://live.bilibili.com/26332543

qrcode



Session Chair: Prof. Chengtao Ji

Xi'an Jiaotong-Liverpool University







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.