Minsuk Kahng, Assistant Professor
School of EECS, Oregon State University
How can we make AI more interpretable and accessible, so that people can build them more easily and use them more effectively? In this talk, I present my human-centric approach to this challenging problem, by creating novel data visualization tools that are scalable, interactive, and easy to use.
I present my work in two interrelated topics: (1) Visual Analytics for Industry-scale Models: I describe how the ActiVis system helps Facebook data scientists interpret their models that use industry-scale datasets.
ActiVis has been deployed on Facebook's ML platform. (2) Broadening People's Access to AI: I show how GAN Lab helps novices interactively learn complex concepts of Generative Adversarial Networks (GANs). It has been open-sourced with Google Brain and used by more than 70,000 people over the world. Lastly, I discuss my vision to bring human into the ML workflow and design interaction model building systems for non-experts.
Minsuk Kahng is an Assistant Professor in the School of EECS at Oregon State University. His research focuses on building interactive tools for exploring, interpreting, and interacting with complex machine learning systems and large datasets. He publishes at premier venues spanning data visualization, databases and data mining, machine learning, and human-computer interaction. Kahng received his Ph.D. in Computer Science from Georgia Tech, and his Ph.D. studies have been supported by a Google PhD Fellowship and an NSF Graduate Research Fellowship.
Wednesday, February 5 at 1:00pm to 2:00pm
Gleeson Hall (Chem Engr), 200
2115 SW Campus Way, Corvallis, OR 97331