The use of disciplines in pure mathematics can increase the reliability and explainability of machine learning models that “transcend human intuition,” according to PNNL scientists.
Research from PNNL and the University of Washington demonstrates the extension of the MBE for periodic systems and its use to decompose the lattice energies of different ice polymorphs.
To overcome high-performance computing bottlenecks, a research team at PNNL proposed using graph theory, a mathematical field that explores relationships and connections between a number, or cluster, of points in a space.
The work by the team at PNNL takes a critical step in leveraging ML to accelerate advanced manufacturing R&D, specifically for manufacturing techniques without access to efficient, first-principles simulations.
Scientists are pioneering approaches in the branch of artificial intelligence known as machine learning to design and train computer software programs that guide the development of new manufacturing processes.
PNNL researchers developed a hybrid quantum-classical approach for coupled-cluster Green’s function theory that maintains accuracy while cutting computational costs.
A Q&A with Lauren Charles, veterinarian and PNNL data scientist, on zoonotic diseases and the role biosurveillance plays in mitigating the growing threat to global health.