Name: Warren Davis
Pronouns: he/him
Biography:
Dr. Warren L. Davis IV is a Principal Member of Technical Staff in the Scientific Machine Learning department in the Center for Computing Research at Sandia National Laboratories. He was the PI for the Hybrid Methods for Cybersecurity Analysis LDRD and the Machine Learning in Adversarial Environments LDRD, research projects which had significant impact on cyber operations at the lab. In addition, he is the PI of the In-Situ Machine Learning for Intelligent Data Capture on Exascale Platforms research project for the DOE ASCR program. Warren joined the technical staff at Sandia in 2009. He received his Ph.D. in computer science from Florida State in 2006, gaining industry experience as a graduate intern at both the National Astronomical Observatory of Japan in Tokyo and the IBM Almaden Research Center, where he was hired as a Research Staff Member after graduation. Warren has published over 20 journal articles, conference publications, peer-reviewed presentations, and a book chapter. He has applied artificial intelligence and data science to the fields of cybersecurity, healthcare informatics, climate modeling, material science, and fluid dynamics, to name a few. In addition, he was awarded the 2019 Black Engineer of the Year Award in Research Leadership.
Institution/Lab: Sandia National Laboratories
Website:
SRP Collaboration Topic/Title: In-Situ Machine Learning
Field or research area: Computer Science
Please select all the topical areas that apply to your project:
Computational Science Applications (i.e., bioscience, cosmology, chemistry, environmental science, nanotechnology, climate, etc.); Data Science (i.e., data analytics, data management & storage systems, visualization); High-Performance Computing; Machine Learning and AI
Brief Abstract:
DOE research often involves discovering new, “interesting” events in high-fidelity physics-based HPC simulations. Standard anomaly detection algorithms are limited, requiring the capture of all the data for post processing, or requiring high-bandwidth in-situ communication. Our research focuses on creating more efficient ways to detect anomalies in-situ, thus facilitating more precisely targeted event capture.
Desired relevant skills, background, or interests:
Python programming Mathematics
Other comments:
Do any special requirements apply? Minimum GPA (specify what GPA in comments below)
Other, specify:
Keywords:
Artificial Intelligence; Machine Learning; Data Science; Anomaly Detection; Deep Learning; Deep Neural Networks; Clustering
Lightning Talk Title: Artificial Intelligence for Science and Engineering