Back to Table of contents

Primeur weekly 2019-07-08

Quantum computing

Leading European institutions partner with IBM to accelerate joint research and educational opportunities in quantum computing ...

Puzzling on a quantum chessboard ...

Simulating quantum systems with neural networks ...

Quantum - widening the net ...

Sigma-i and D-Wave announce largest-ever quantum Cloud-access contract ...

Rigetti Computing awarded as Technology Pioneer by World Economic Forum ...

Accenture awarded second U.S. patent for quantum computing ...

Generation and sampling of quantum states of light in a silicon chip ...

Quantum technology R&D programme between Ben-Gurion University, IDF and US Defense Departments announced ...

Focus on Europe

Spring 2019 edition of the e-IRG Magazine available ...

Middleware

NEC server software enables advanced and secure login to websites in compliance with FIDO2 ...

Hardware

'Tsunami' on a silicon chip: a world first for light waves ...

Applications

Atos and GENCI announce winners of Atos Joseph Fourier Award 2019 ...

Baidu named development partner on Intel Nervana Neural Network Processor for Training ...

Using artificial intelligence to better predict severe weather ...

Using machine learning models to better predict bladder cancer stages ...

A data-driven journey to the center of the earth ...

Building a brain ...

Researchers cast neural nets to simulate molecular motion ...

Theoretical physicists unveil one of the most ubiquitous and elusive concepts in chemistry ...

The Cloud

Atos expands strategic partnership with Google Cloud to enable Oracle database customers to benefit from Google Cloud Platform ...

SDSC's Sherlock division debuts Innovation Accelerator Platforms ...

Researchers cast neural nets to simulate molecular motion


New deep learning models predict the interactions between atoms in organic molecules. These models will help computational biologists and drug development researchers understand and treat disease. Credit: Los Alamos National Laboratory.
2 Jul 2019 Los Alamos - New work from Los Alamos National Laboratory, the University of North Carolina at Chapel Hill, and the University of Florida is showing that artificial neural nets can be trained to encode quantum mechanical laws to describe the motions of molecules, supercharging simulations potentially across a broad range of fields.

"This means we can now model materials and molecular dynamics billions of times faster compared to conventional quantum methods, while retaining the same level of accuracy", stated Justin Smith, Los Alamos physicist and Metropolis Fellow in the laboratory's Theoretical Division. Understanding how molecules move is critical to tapping their potential value for drug development, protein simulations and reactive chemistry, for example, and both quantum mechanics and experimental (empirical) methods feed into the simulations.

The new technique, called the ANI-1ccx potential, promises to advance the capabilities of researchers in many fields and improve the accuracy of machine learning-based potentials in future studies of metal alloys and detonation physics.

Quantum mechanical (QM) algorithms, used on classical computers, can accurately describe the mechanical motions of a compound in its operational environment. But QM scales very poorly with varying molecular sizes, severely limiting the scope of possible simulations. Even a slight increase in molecular size within a simulation can dramatically increase the computational burden. So practitioners often resort to using empirical information, which describes the motion of atoms in terms of classical physics and Newton's Laws, enabling simulations that scale to billions of atoms or millions of chemical compounds.

Traditionally, empirical potentials have had to strike a trade-off between accuracy and transferability. When the many parameters of the potential are finely tuned for one compound, the accuracy decreases on other compounds.

Instead, the Los Alamos team, with the University of North Carolina at Chapel Hill and University of Florida, has developed a machine learning approach called transfer learning that lets them build empirical potentials by learning from data collected about millions of other compounds. The new approach with the machine learning empirical potential can be applied to new molecules in milliseconds, enabling research into a far greater number of compounds over much longer timescales.

J. S. Smith, B. T. Nebgen, R. Zubatyuk, N. Lubbers, C. Devereux, K. Barros, S. Tretiak, O. Isayev, and A.E. Roitberg are the authors of the paper titled " Approaching coupled cluster accuracy with a general-purpose neural network potential through transfer learning " published inNature Communications- 10.1038/s41467-019-10827-4 (2019).

Source: DOE/Los Alamos National Laboratory

Back to Table of contents

Primeur weekly 2019-07-08

Quantum computing

Leading European institutions partner with IBM to accelerate joint research and educational opportunities in quantum computing ...

Puzzling on a quantum chessboard ...

Simulating quantum systems with neural networks ...

Quantum - widening the net ...

Sigma-i and D-Wave announce largest-ever quantum Cloud-access contract ...

Rigetti Computing awarded as Technology Pioneer by World Economic Forum ...

Accenture awarded second U.S. patent for quantum computing ...

Generation and sampling of quantum states of light in a silicon chip ...

Quantum technology R&D programme between Ben-Gurion University, IDF and US Defense Departments announced ...

Focus on Europe

Spring 2019 edition of the e-IRG Magazine available ...

Middleware

NEC server software enables advanced and secure login to websites in compliance with FIDO2 ...

Hardware

'Tsunami' on a silicon chip: a world first for light waves ...

Applications

Atos and GENCI announce winners of Atos Joseph Fourier Award 2019 ...

Baidu named development partner on Intel Nervana Neural Network Processor for Training ...

Using artificial intelligence to better predict severe weather ...

Using machine learning models to better predict bladder cancer stages ...

A data-driven journey to the center of the earth ...

Building a brain ...

Researchers cast neural nets to simulate molecular motion ...

Theoretical physicists unveil one of the most ubiquitous and elusive concepts in chemistry ...

The Cloud

Atos expands strategic partnership with Google Cloud to enable Oracle database customers to benefit from Google Cloud Platform ...

SDSC's Sherlock division debuts Innovation Accelerator Platforms ...