Did you know we have a monthly newsletter? View past volumes and subscribe.
Lab offers forum on machine learning for industry
April 22, 2021 -
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. The event is sponsored by LLNL’s High Performance Computing Innovation Center and the Data Science Institute. The deadline for submitting presentations or industry use cases is June 30. The...
COVID-19 HPC Consortium reflects on past year
April 1, 2021 -
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 with free access to...
ATOM Consortium welcomes 3 DOE national labs to accelerate drug discovery
March 29, 2021 -
The Accelerating Therapeutics for Opportunities in Medicine (ATOM) consortium, of which LLNL is part, announced the U.S. Department of Energy’s Argonne, Brookhaven and Oak Ridge national laboratories are joining the consortium to further develop ATOM’s AI-driven drug discovery platform. The public-private ATOM consortium aims to transform drug discovery from a slow, sequential and high-risk...
Winter hackathon highlights data science talks and tutorial
March 24, 2021 -
The Data Science Institute (DSI) sponsored LLNL’s 27th hackathon on February 11–12. Held four times a year, these seasonal events bring the computing community together for a 24-hour period where anything goes: Participants can focus on special projects, learn new programming languages, develop skills, dig into challenging tasks, and more. The winter hackathon was the DSI’s second such...
Novel deep learning framework for symbolic regression
March 18, 2021 -
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 Representations (ICLR 2021), one of the top machine learning...
Ana Kupresanin featured in FOE alumni spotlight
March 10, 2021 -
LLNL's Ana Kupresanin, deputy director of the Center for Applied Scientific Computing and member of the Data Science Institute council, was recently featured in a Frontiers of Engineering (FOE) alumni spotlight. Kupresanin develops statistical and machine learning models that incorporate real-world variability and probabilistic behavior to quantify uncertainties in engineering and physics...
'Self-trained' deep learning to improve disease diagnosis
March 4, 2021 -
New work by computer scientists at 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 February 19. The technique, which includes novel regularization and “self-training” strategies, addresses some well-known challenges in the...
CASC research in machine learning robustness debuts at AAAI conference
Feb. 10, 2021 -
LLNL’s Center for Applied Scientific Computing (CASC) has steadily grown its reputation in the artificial intelligence (AI)/machine learning (ML) community—a trend continued by three papers accepted at the 35th AAAI Conference on Artificial Intelligence, held virtually on February 2–9, 2021. Computer scientists Jayaraman Thiagarajan, Rushil Anirudh, Bhavya Kailkhura, and Peer-Timo Bremer led...
Lab researchers explore ‘learn-by-calibration’ approach to deep learning to accurately emulate scientific process
Feb. 10, 2021 -
An LLNL team has developed a “Learn-by-Calibrating” method for creating powerful scientific emulators that could be used as proxies for far more computationally intensive simulators. Researchers found the approach results in high-quality predictive models that are closer to real-world data and better calibrated than previous state-of-the-art methods. The LbC approach is based on interval...
LLNL physicist wins Young Former Student award
Dec. 16, 2020 -
Texas A&M University’s Department of Nuclear Engineering on December 10 announced it has honored LLNL physicist Kelli Humbird with its 2020-21 Young Former Student award for her work at LLNL in combining machine learning with inertial confinement fusion (ICF) research. Humbird graduated from Texas A&M with a PhD in nuclear engineering in 2019. Since joining the Laboratory as an intern in 2016...
NeurIPS papers aim to improve understanding and robustness of machine learning algorithms
Dec. 7, 2020 -
The 34th Conference on Neural Information Processing Systems (NeurIPS) is featuring two papers advancing the reliability of deep learning for mission-critical applications at LLNL. The most prestigious machine learning conference in the world, NeurIPS began virtually on Dec. 6. The first paper describes a framework for understanding the effect of properties of training data on the...
Model for COVID-19 drug discovery a Gordon Bell finalist
Nov. 17, 2020 -
A machine learning model developed by a team of LLNL scientists to aid in COVID-19 drug discovery efforts is a finalist for the Gordon Bell Special Prize for High Performance Computing-Based COVID-19 Research. Using Sierra, the world’s third fastest supercomputer, LLNL scientists produced a more accurate and efficient generative model to enable COVID-19 researchers to produce novel compounds...
From intern to mentor, Nisha Mulakken builds a career in bioinformatics
Nov. 3, 2020 -
The COVID-19 pandemic has sparked a wave of new research and development at the Lab, and Nisha Mulakken is very busy. The biostatistician has enhanced the Lawrence Livermore Microbial Detection Array (LLMDA) system with detection capability for all variants of SARS-CoV-2. The technology detects a broad range of organisms—viruses, bacteria, archaea, protozoa, and fungi—and has demonstrated...
The internship that launched a machine-learning target revolution
Oct. 1, 2020 -
Kelli Humbird came to LLNL as a student intern and became a teacher of new data science techniques. In this profile, she describes her experiences and the path that led to her research inertial confinement fusion. Read more at the National Ignition Facility.
Using models, 3D printing to study common heart defect
Aug. 10, 2020 -
One of the most common congenital heart defects, coarctation of the aorta (CoA) is a narrowing of the main artery transporting blood from the heart to the rest of the body. It affects more than 1,600 newborns each year in the United States, and can lead to health issues such as hypertension, premature coronary artery disease, aneurysms, stroke and cardiac failure. To better understand risk...
Advancing healthcare with data science (VIDEO)
Aug. 3, 2020 -
This video provides an overview of projects in which data scientists work with domain scientists to address major challenges in healthcare. To help fight the COVID-19 pandemic, researchers are developing computer models to search for potential antibody and antiviral drug treatments, sharing a data portal with scientists and the general public, and analyzing drug compounds via a novel text...
Machine learning model may perfect 3D nanoprinting
July 29, 2020 -
Two-photon lithography (TPL)—a widely used 3D nanoprinting technique that uses laser light to create 3D objects—has shown promise in research applications but has yet to achieve widespread industry acceptance due to limitations on large-scale part production and time-intensive setup. LLNL scientists and collaborators turned to machine learning to address two key barriers to industrialization...
Lockdown doesn’t hinder annual Data Science Challenge
June 26, 2020 -
Due to the COVID-19 pandemic and shelter-in-place restrictions, this year’s Data Science Challenge with the University of California, Merced was an all-virtual offering. The two-week challenge involved 21 UC Merced students who worked from their homes through video conferencing and chat programs to develop machine learning models capable of differentiating potentially explosive materials from...
DL-based surrogate models outperform simulators and could hasten scientific discoveries
June 17, 2020 -
Surrogate models supported by neural networks can perform as well, and in some ways better, than computationally expensive simulators and could lead to new insights in complicated physics problems such as inertial confinement fusion (ICF), LLNL scientists reported. Read more at LLNL News.
Modeling neuronal cultures on 'brain-on-a-chip' devices
June 12, 2020 -
For the past several years, LLNL scientists and engineers have made significant progress in development of a three-dimensional “brain-on-a-chip” device capable of recording neural activity of human brain cell cultures grown outside the body. The team has developed a statistical model for analyzing the structures of neuronal networks that form among brain cells seeded on in vitro brain-on-a...