Trusted and Responsible AI
PNNL has developed a tool suite of interactive analytics that can be rapidly integrated into analyst workflows to empirically analyze and gain qualitative understanding of AI model performance jointly across dimensions.
Henry Accepts Joint Appointment with Texas A&M University
Michael Henry, a senior data scientist at PNNL, has accepted a joint appointment at the Texas A&M University RELLIS Center for Applied Research and Experiential Learning.
PNNL Papers on Machine Learning Accepted to AAAI-21
PNNL data scientists Henry Kvinge and Ted Fujimoto presented their research on few-shot learning and reinforcement learning, respectively, at workshops during the 2021 AAAI Conference on Artificial Intelligence.
Explainable AI: A Must for Nuclear Nonproliferation, National Security
Explainable AI helps scientists understand and untangle the threads of information that the system uses to make choices or recommendations.
Decoding the “Black Box” of AI to Tackle National Security Concerns
Explainable artificial intelligence—understanding and explaining the reasoning behind AI decisions—is a necessity for national security.
PNNL Using 5G to Unlock New Potential
One year ago, Verizon announced a partnership that made PNNL the U.S. Department of Energy’s first national laboratory with Verizon 5G ultra-wideband wireless technology.
Machine Learning Scientists Teach Computers to Read X-Ray Images
PNNL researchers used machine learning to develop a tool for a nonprofit to identify orthopedic implants in X-ray images to improve surgical speed and accuracy.
Machine Learning for Synchrophasor Analysis
Journal Highlights Future of AI and Emergency Management
A team from PNNL contributed several articles to the Domestic Preparedness Journal showcasing recent efforts to explore the emergency management and artificial intelligence research and development landscape.