*********************************
There is now a CONTENT FREEZE for Mercury while we switch to a new platform. It began on Friday, March 10 at 6pm and will end on Wednesday, March 15 at noon. No new content can be created during this time, but all material in the system as of the beginning of the freeze will be migrated to the new platform, including users and groups. Functionally the new site is identical to the old one. webteam@gatech.edu
*********************************
Title
EMPOWERING USERS TO COMMUNICATE THEIR PREFERENCES TO MACHINE LEARNING MODELS IN VISUAL ANALYTICS
Subhajit Das
PhD Candidate in Computer Science
School of Interactive Computing
Georgia Institute of Technology
Date: Friday, November 20, 2020
Time: 4:00pm - 6:00pm EST (virtual)
Location: (remote via MS Teams, see below)
Committee
Dr. Alex Endert - Advisor, Georgia Institute of Technology, School of Interactive Computing
Dr. John Stasko - Georgia Institute of Technology, School of Interactive Computing
Dr. Polo Chau - Georgia Institute of Technology, School of Interactive Computing
Dr. Thomas Ploetz - Georgia Institute of Technology, School of Interactive Computing
Dr. Remco Chang - Tufts University, School of Computer Science
Abstract
Recent visual analytic (VA) systems rely on machine learning (ML) to allow users perform a variety of data analytic tasks, e.g., biologists clustering genome samples, medical practitioners predicting the diagnosis for a new patient, ML practitioners tuning models' hyperparameter settings etc. These VA systems support interactive construction of models to people (I call them power users) with a diverse set of expertise in ML; from non-experts, to intermediates, to expert ML users. However, designing VA systems for power users poses various challenges, such as addressing diversity in user expertise, metric selection, user modeling to automatically infer preferences, evaluating the success of these systems, etc. Through my research, I investigate how power users can communicate their preferences to interactively construct machine learning models in support of various data analytic goals. Specifically, I explore and analyze several VA techniques such as multi-model steering, model selection, interactive objective functions, conflict resolution in objective functions etc. to facilitate specification of user goals and objectives to underlying model(s) using VA systems. In the end, I summarize my contribution(s) and then reflect on assumptions, strengths, and limitations of the research to inform potential future direction of this work.
MS Teams Meeting Invitation
Medium: (Via MS Teams on Chrome/MS Edge browser or MS Teams App.)
________________________________________________________________________________
Microsoft Teams meeting
Join on your computer or mobile app
Click here to join the meeting
