News Center
Advancing New Battery Design with Deep Learning
A team of researchers from Berkeley Lab and UC Irvine has developed deep-learning algorithms designed to automate the quality control and assessment of new battery designs for electric cars. Read More »
Michael Mahoney Tapped to Lead the Machine Learning and Analytics Group
Berkeley Lab’s Scientific Data Division recently appointed Michael Mahoney to lead its Machine Learning and Analytics Group.
Read More »
Berkeley Lab Computing Resources Enable Deeper Understanding of Supernovae Explosions
An international research team recently made history by recording the earliest post-explosion detection of a Type Ia supernova, using cosmological models developed at Berkeley Lab and supercomputing resources at NERSC. Read More »
HYPPO: Leveraging Prediction Uncertainty to Optimize Deep Learning Models for Science
With a growing need for optimization tools that can enhance deep learning models and their training to improve predictive capabilities and accelerate time-consuming computer simulations, a Berkeley Lab team developed HYPPO, an open-source software tool for hyperparameter optimization of deep neural networks. Read More »
Open Sourced Control Hardware for Quantum Computers
To make engineering quantum hardware more accessible, the Advance Quantum Testbed has open-sourced a new electronics control and measurement system for superconducting quantum processors. Read More »
Cutting Through the Noise
Berkeley Lab’s AMCR and Physics divisions joined forces to create a new approach to quantum error mitigation - "noise estimation circuits" - that could help make quantum computing’s theoretical potential a reality. Read More »
AMCRD’s Sherry Li Part of Team Honored by SIAM for Best Paper
AMCRD's Sherry Li is co-author on a paper being honored with the 2022 SIAM Activity Group on Supercomputing Best Paper Prize. Read More »
SIMCoV Models Cell-by-Cell Spread of Respiratory Infections
Berkeley Lab computational research scientist Steve Hofmeyr is part of a team that developed SimCoV, which can provide a 3D simulation of a portion of the lung and model the ways in which COVID-19 and other viral infections spread in the lungs. Read More »
Berkeley Lab’s FasTensor Provides Pain-Free Big Data Analysis
With FasTensor, researchers in Berkeley Lab’s Scientific Data Management Group developed an open source tool to help its users efficiently process and analyze their massive datasets. Read More »