LLNL
LLNL Establishes AI Innovation Incubator To Advance Artificial Intelligence For Applied Science
Lawrence Livermore National Laboratory (LLNL) has established the AI Innovation Incubator (AI3), a collaborative hub aimed at uniting experts in artificial intelligence (AI) from LLNL, industry and academia to advance AI for large-scale scientific and commercial applications. LLNL has entered into a new memoranda of understanding with Google, IBM and NVIDIA, with plans to use the incubator to facilitate discussions and form …
Registrations Ongoing For Virtual Forum On Industrial Machine Learning Applications
Registration is open through July 29 for the first-ever Machine Learning for Industry Forum (ML4I), a three-day virtual event starting Aug. 10. The forum aims to foster and illustrate the adoption of machine learning methods for practical industrial outcomes, with a strong emphasis on manufacturing. Over the course of the event, attendees will engage in …
Machine Learning Aids In Materials Design
Scientists developed a machine learning algorithm to predict 3D molecular crystal density from 2D chemical structures. A long-held goal by chemists across many industries, including energy, pharmaceuticals, energetics, food additives and organic semiconductors, is to imagine the chemical structure of a new molecule and be able to predict how it will function for a desired …
Satellites May Have Underestimated Warming In The Lower Atmosphere
New research by Lawrence Livermore National Laboratory (LLNL) climate scientists and collaborators shows that satellite measurements of the temperature of the troposphere (the lowest region of the atmosphere) may have underestimated global warming over the last 40 years. The research appears in the Journal of Climate The team studied four different properties of tropical climate …
The Data-Driven Future Of Extreme Physics
By applying modern machine learning and data science methods to “extreme” plasma physics, researchers can gain insight into our universe and find clues about creating a limitless amount of energy. In a recent perspective published in Nature, Lawrence Livermore National Laboratory (LLNL) scientists and international collaborators outline key challenges and future directions in using machine …
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 practical industrial …
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 Representations (ICLR 2021), one of the top machine …
‘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” strategies, …
Lab Launches Interdisciplinary Space Science Institute
What are the next world-class, game-changing concepts and technologies that will address the most important questions in astrophysics or planetary science? Lawrence Livermore National Laboratory (LLNL) researchers will soon be better equipped to answer this question with the launch this month of a new Space Science Institute (SSI), intended to boost cross-discipline collaboration and discovery. …
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 could be used as proxies …