Results 41 to 50 of about 15,175 (257)

h-Analysis and data-parallel physics-informed neural networks

Scientific Reports, 2023
We explore the data-parallel acceleration of physics-informed machine learning (PIML) schemes, with a focus on physics-informed neural networks (PINNs) for multiple graphics processing units (GPUs) architectures. In order to develop scale-robust and high-
Paul Escapil-Inchauspé, Gonzalo A. Ruz
doaj   +1 more source

Physics-informed neural networks for diffraction tomography

Advanced Photonics, 2022
We propose a physics-informed neural network as the forward model for tomographic reconstructions of biological samples. We demonstrate that by training this network with the Helmholtz equation as a physical loss, we can predict the scattered field accurately.
Saba, Amirhossein, Gigli, Carlo, Ayoub, Ahmed B., Psaltis, Demetri   +3 more
openaire   +3 more sources

Phosphoinositides and inositol phosphates as molecular glues

FEBS Letters, EarlyView.
Inositol phosphates (IPs) and phosphoinositides (PIPs) regulate diverse eukaryotic processes. Beyond recruiting signaling proteins or acting as structural cofactors, recent studies suggest they mediate protein–protein interactions as natural molecular glues.
Aleshia Seaton‐Terry, Alexander J. Cutright, Mong Na Claire Loi, Jessica Martin, Joseph W. Gilligan, Jakub N. Kubina, Michael J. Arambula, Susanna Tanada Palmu, Daniella Zhou, Raymond D. Blind   +9 more
wiley   +1 more source

A Taxonomic Survey of Physics-Informed Machine Learning

Applied Sciences, 2023
Physics-informed machine learning (PIML) refers to the emerging area of extracting physically relevant solutions to complex multiscale modeling problems lacking sufficient quantity and veracity of data with learning models informed by physically relevant
Joseph Pateras, Pratip Rana, Preetam Ghosh   +2 more
doaj   +1 more source

Evidential Physics-Informed Neural Networks

CoRR
We present a novel class of Physics-Informed Neural Networks that is formulated based on the principles of Evidential Deep Learning, where the model incorporates uncertainty quantification by learning parameters of a higher-order distribution. The dependent and trainable variables of the PDE residual loss and data-fitting loss terms are recast as ...
Hai Siong Tan, Kuancheng Wang, Rafe McBeth   +2 more
openaire   +2 more sources

Modelling stem cell differentiation related processes—A practical overview for biologists

FEBS Letters, EarlyView.
Stem cell differentiation is complex and difficult to control experimentally. This review introduces suitable computational modelling approaches that can support stem cell research, from mechanistic ODE and abstract models to multiscale and deep learning methods.
Ricco Zeegelaar, Xinqi Yan, Lucas F. Jansen Klomp, Stefano Schivo, Janine N. Post   +4 more
wiley   +1 more source

Physics-Informed Neural Networks and Extensions

CoRR
Frontiers of Science Awards ...
Maziar Raissi, Paris Perdikaris, Nazanin Ahmadi Daryakenari, George Em Karniadakis   +3 more
openaire   +2 more sources

From tumor‐centric to ecosystem‐based hypotheses in brain tumor research and care

Molecular Oncology, EarlyView.
Primary brain tumors, whether in adults or children, present a major challenge because of their dramatic prognosis and the ongoing lack of efficient therapeutic approaches. In recent years, a shift has occurred from tumor‐centric concepts to a more holistic view of these tumors as dynamic ecosystems.
Julie Gavard, Flavie Bénard, Eva Billat, Margaux Le Guyon, Victoria Maltret, Laura Merlet, Chloé Astrid Walter, Tony Avril, Eric Chevet   +8 more
wiley   +1 more source

Conformalized Physics-Informed Neural Networks

CoRR
Physics-informed neural networks (PINNs) are an influential method of solving differential equations and estimating their parameters given data. However, since they make use of neural networks, they provide only a point estimate of differential equation parameters, as well as the solution at any given point, without any measure of uncertainty. Ensemble
Lena Podina, Mahdi Torabi Rad, Mohammad Kohandel   +2 more
openaire   +2 more sources

Directed evolution of enzymes at the crossroads of tradition and innovation

FEBS Open Bio, EarlyView.
An iterative cycle of data‐driven enzyme optimization comprising four stages: genetic diversification of a template enzyme, expression of protein variants, high‐throughput evaluation, and machine‐learning‐guided redesign of the next variant library.
Maria Tomkova, Andrej Mirossay, Erik Sedlak   +2 more
wiley   +1 more source