Chellappa Chairs National Academy Workshop on Machine Learning

Minta Martin Professor Rama Chellappa (ECE/UMIACS/CS) chaired a National Academies of Science, Engineering, and Medicine Workshop on Robust Machine Learning Algorithms and Systems for Detection and Mitigation of Adversarial Attacks and Anomalies on December 11-12, 2018, in Berkeley, California. Proceedings were recently published that summarize the presentations and discussions held during the 2-day workshop.

The goal of this workshop was to discuss methods and systems for assuring the Quality of Machine-Generated Analytic Products from Multi-Source Data. Chellappa, who is a Distinguished University Professor and one of the top researchers in the world in artificial intelligence and machine learning, was elected to chair the workshop planning committee.

During the session on Recent Trends in Machine Learning, Chellappa gave a presentation titled “Generative Adversarial Networks (GANS) For Domain Adaptation and Security against Attacks.” In his talk, Chellappa spoke on the recent shift of focus from physics and geometry to data in the computer vision field. He discussed the use of generative adversarial networks (GANs) for unsupervised domain adaptation and semantic segmentation as well as protecting against adversarial attacks. To conclude, Chellappa addressed near and long-term research opportunities for the field of computer vision. More about Chellappa’s talk can be read here.

Published September 13, 2019