The University of Arizona

Machine Learning-Enhanced Visualization

Machine Learning-Enhanced Visualization

Series: Tripods
Location: ENR 2 S210
Presenter: Matthew Berger, UA Computer Science

Due to the rapid growth and availability of data in recent years, machine learning has emerged as a powerful tool for automated data analysis, with success in such tasks as text-based document classification and visual recognition. However, for exploratory analyses or formulating hypotheses, machine learning alone cannot be used, as it is essential for a human in the loop to lead the analysis. In such cases, data visualization is an indispensable tool to help people interact with and make sense of data. Yet visualization should not completely eschew machine learning, due to the possible affordances machine learning can bring for visualization. In this talk, I will focus on how machine learning models can be used to enhance visualization. I will first show how to enhance the task of interactive document exploration by using specific properties of neural language models built from large amounts of text data. Secondly, I will show how to enhance the visualization of volumetric data by using generative models that learn the distribution of visual outputs produced from a volume renderer.

Department of Mathematics, The University of Arizona 617 N. Santa Rita Ave. P.O. Box 210089 Tucson, AZ 85721-0089 USA Voice: (520) 621-6892 Fax: (520) 621-8322 Contact Us © Copyright 2018 Arizona Board of Regents All rights reserved