Back
Computing
Conference papers highlight importance of data security to machine learning
The 2021 Conference on Computer Vision and Pattern Recognition, the premier conference of its kind, will feature two papers co-authored by a Lawrence Livermore National Laboratory (LLNL) researcher targeted at improving the understanding of robust machine learning models. Both papers include contributions from LLNL computer scientist Bhavya Kailkhura and examine the…
Students build knowledge of machinist trade during Lab's first-ever virtual Manufacturing Workshop
The COVID-19 pandemic didn’t prevent local high school students from learning what it’s like to be one of the more than 150 machinists who work at Lawrence Livermore National Laboratory (LLNL) during the Materials Engineering Division’s (MED) Manufacturing Workshop, held April 20-22. Students attended the three-day workshop virtually after their school days ended, where…
Advanced Data Analytics for Proliferation Detection shares technical advances during two-day meeting
The Advanced Data Analytics for Proliferation Detection (ADAPD) program held a two-day virtual technical exchange meeting recently. The goal of the meeting was to highlight the science-based and data-driven analysis work conducted by ADAPD to advance the state-of-the-art to accelerate artificial intelligence (AI) innovation and develop AI-enabled systems to enhance the…
Lawrence Livermore takes part in international planetary defense conference
Ten scientists from Lawrence Livermore National Laboratory (LLNL) last week took part in the 7th IAA Planetary Defense Conference (PDC), hosted by the United Nations Office for Outer Space Affairs in cooperation with the European Space Agency. Megan Bruck Syal, who helped lead the Lab’s participation in the event and who also was a conference session chair, said this year…
HPC4Energy Innovation kicks off spring solicitation
The Department of Energy’s High Performance Computing for Energy Innovation (HPC4EI) Initiative is accepting industry proposals for projects leveraging the world-class supercomputing and expertise of DOE national laboratories to address key energy-related challenges in domestic manufacturing. The DOE Office of Energy Efficiency and Renewable Energy’s Advanced Manufacturing…
Krell Institute honors Hittinger with Corones Award
The Krell Institute, a nonprofit organization serving the scientific and educational communities, has awarded Lawrence Livermore National Laboratory (LLNL) computational scientist Jeff Hittinger with its 2021 James Corones Award in Leadership, Community Building and Communication. The award, named for the institute’s founder, recognizes mid-career scientists and engineers…
LLNL, IBM and Red Hat joining forces to explore standardized HPC resource management interface
Lawrence Livermore National Laboratory (LLNL), IBM and Red Hat are combining forces to develop best practices for interfacing high performance computing (HPC) schedulers and cloud orchestrators, an effort designed to prepare for emerging supercomputers that take advantage of cloud technologies. Under a recently signed memorandum of understanding (MOU), researchers aim to…
Lab offers forum on machine learning for industry
Lawrence Livermore National Laboratory (LLNL) is looking for participants and attendees from industry, research institutions and academia for the first-ever Machine Learning for Industry Forum (ML4I), a three-day virtual event starting Aug. 10. Pre-registrations are open for the forum, which aims to foster and illustrate the adoption of machine learning methods for…
De Supinski named one of HPCwire’s 'People to Watch'
Bronis R. de Supinski, Lawrence Livermore National Laboratory’s (LLNL) chief technology officer (CTO) for Livermore Computing (LC), is one of the top influencers in the high performance computing industry for 2021, according to HPCwire. On April 7, the publication honored de Supinski as one of its "People to Watch," a group of 14 “innovators and visionaries building and…
COVID-19 HPC Consortium reflects on past year
COVID-19 HPC Consortium scientists and stakeholders met virtually on March 23 to mark the consortium’s one-year anniversary, discussing the progress of research projects and the need to pursue a broader organization to mobilize supercomputing access for future crises. The White House announced the launch of the public-private consortium, which provides COVID-19 researchers…
Novel deep learning framework for symbolic regression
Lawrence Livermore National Laboratory (LLNL) computer scientists have developed a new framework and an accompanying visualization tool that leverages deep reinforcement learning for symbolic regression problems, outperforming baseline methods on benchmark problems. The paper was recently accepted as an oral presentation at the International Conference on Learning…
Lab event encourages growth of women in data science
Coinciding with International Women’s Day on March 8, Lawrence Livermore National Laboratory’s 4th Women in Data Science (WiDS) regional event brought women together to discuss successes, opportunities and challenges of being female in a mostly male field. The Lab’s first-ever virtual WiDS gathering attracted dozens of LLNL data scientists as well as some from outside the…
Research uncovers missing physics in explosive hotspots
Research conducted on Lawrence Livermore National Laboratory’s (LLNL) supercomputer Quartz highlights findings made by scientists that reveal a missing aspect of the physics of hotspots in TATB (1,3,5-trimamino-2,4,6-trinitrobenzene) and other explosives. Hotspots are localized regions of elevated temperature that form from shock-induced collapse of microstructural…
'Self-trained' deep learning to improve disease diagnosis
New work by computer scientists at Lawrence Livermore National Laboratory (LLNL) and IBM Research on deep learning models to accurately diagnose diseases from X-ray images with less labeled data won the Best Paper award for Computer-Aided Diagnosis at the SPIE Medical Imaging Conference on Feb. 19. The technique, which includes novel regularization and “self-training”…
Retiring Director Bill Goldstein leaves behind a rich legacy of extraordinary growth, innovation for the Lab
Nearly a year into piloting a major scientific institution through one of the most taxing and disruptive global events in modern history, outgoing Livermore Lab Director Bill Goldstein is ready for a vacation. One of Goldstein’s first orders of business following his retirement on March 1 is returning to the lush slopes, coffee plantations and sandy beaches of Kona, Hawaii…
Lab researchers explore ‘learn-by-calibration’ approach to deep learning to accurately emulate scientific process
Lawrence Livermore National Laboratory (LLNL) computer scientists have developed a new deep learning approach to designing emulators for scientific processes that is more accurate and efficient than existing methods. In a paper published by Nature Communications, an LLNL team describes a “Learn-by-Calibrating” (LbC) method for creating powerful scientific emulators that…
Kim Budil selected as director of Lawrence Livermore
Kim Budil has been named director of Lawrence Livermore National Laboratory (LLNL). Charlene Zettel, chair of Lawrence Livermore National Security, LLC (LLNS), which manages the Laboratory for the Department of Energy's (DOE) National Nuclear Security Administration (NNSA), made the announcement to Laboratory employees Jan. 28. Budil will begin her new role on March 2…
Lawrence Livermore's '2020 Year in Review'
Though 2020 was dominated by events surrounding the COVID-19 pandemic — whether it was adapting to social distancing and the need to telecommute, safeguarding employees as they returned to conduct mission-essential work or engaging in COVID-related research — Lawrence Livermore National Laboratory (LLNL) managed an exceptional year in all facets of science and technology…
Lawrence Livermore computer scientist heads award-winning computer vision research
The 2021 IEEE Winter Conference on Applications of Computer Vision (WACV 2021) on Wednesday announced that a paper co-authored by a Lawrence Livermore National Laboratory (LLNL) computer scientist received the conference’s Best Paper Honorable Mention award based on its potential impact to the field. The paper, titled "Generative Patch Priors for Practical Compressive…
LLNL develops optical capability for thin-film neural implants to look into brain activity
Combining hybrid polymer materials with microfabrication and 3D printing, Lawrence Livermore National Laboratory (LLNL) has developed an ultra-compact, lightweight and minimally invasive optoelectronic neural implant that could be used for long-term studies of brain activity. The new implantable devices are built upon a new platform LLNL researchers are calling POEMS …
