Results 101 to 110 of about 16,890,236 (293)

Surrogate modeling for uncertainty quantification in nonlinear dynamics

open access: yes
Predicting the behavior of complex systems in engineering often involves significant uncertainty about operating conditions, such as external loads, environmental effects, and manufacturing variability. As a result, uncertainty quantification (UQ) has become a critical tool in modeling-based engineering, providing methods to identify, characterize, and
Marelli, S., Schär, S., Sudret, B.
openaire   +2 more sources

Intelligent regulation of urban drainage systems based on graph neural network surrogate models

open access: yesShui kexue jinzhan
To address the challenge of balancing accurate simulation with efficient control in the real-time control of urban drainage systems,this study proposed an intelligent real-time control framework integrating a graph neural network (GNN) surrogate model ...
Chutian ZHOU   +4 more
doaj   +1 more source

Smaller is better: nanobodies meet NMR

open access: yesFEBS Letters, EarlyView.
Nanobodies are single‐domain antigen‐binding fragments derived from camelid heavy chain antibodies. Their small size, high stability, and exceptional specificity make nanobodies uniquely useful probes for NMR studies of protein dynamics, transient conformational states, and protein–protein interactions.
Oleg Y. Dmitriev
wiley   +1 more source

Convolutional Neural Networks-Based Lung Nodule Classification: A Surrogate-Assisted Evolutionary Algorithm for Hyperparameter Optimization

open access: yes, 2021
This article investigates deep neural networks (DNNs)-based lung nodule classification with hyperparameter optimization. Hyperparameter optimization in DNNs is a computationally expensive problem, and a surrogate-Assisted evolutionary algorithm has been ...
Zhang, Miao   +5 more
core   +1 more source

Mechanistic Interpretability of Learned Dynamical Surrogate Models [PDF]

open access: yes
This thesis shows that trained Rectified Linear Unit (ReLU) based Recurrent Neural Networks (RNN) do not have to remain black boxes but can be analysed as dynamical systems whose fixed points, manifolds, and bifurcations reveal the underlying computational mechanisms.
openaire   +1 more source

Going viral − Virus‐targeting nanobodies for research, diagnostics and therapy

open access: yesFEBS Letters, EarlyView.
The increasing prevalence of viral diseases represents a major threat for global human health. Nanobodies, small binding fragments derived from camelid heavy‐chain antibodies, offer versatile tools for viral research, diagnostics, and antiviral therapy.
Domenic Ebert, Ulrich Rothbauer
wiley   +1 more source

Soft motions encoded by the fold and mediated by conserved hinge sites drive V‐ATPase allosteric machinery and autoinhibition

open access: yesFEBS Letters, EarlyView.
Vacuolar H+‐ATPase (V‐ATPase) is a multisubunit rotary proton pump that acidifies intracellular compartments. Using elastic network models, we identified conserved hinge residues that govern its large‐scale functional motions. We show that intrinsically encoded ‘soft modes’ drive critical functional transitions, including rotary catalysis and ...
Diksha Parwana   +3 more
wiley   +1 more source

Comparing the paths of Hedgehog release in artificial and natural settings

open access: yesFEBS Letters, EarlyView.
Hh morphogens require solubilization factors to overcome their tight association with the plasma membrane and signal to distant cells, but the precise functions of these factors are controversial. Here, we use published in vivo observations as the most relevant evidence to test their suggested functions and discuss contradictions and gaps between in ...
Janna Puschmann, Kay Grobe
wiley   +1 more source

Multi-Fidelity Ensemble Kalman Method with Dynamic Mode Decomposition Surrogate

open access: yes, 2023
International audienceAn accurate description of the blood flow dynamic in local areas of interest is a key tool to explain emergence of certain abnormalities like stenosis.
Mollo, Pierre
core  

Artificial intelligence as a surrogate brain: bridging neural dynamical models and data

open access: yesNational Science Review
ABSTRACT Recent breakthroughs in artificial intelligence (AI) are reshaping the way we construct computational counterparts of the brain, giving rise to a new class of ‘surrogate brains’. In contrast to conventional hypothesis-driven biophysical models, the AI-based surrogate brain encompasses a broad spectrum of data-driven ...
Yinuo Zhang   +8 more
openaire   +4 more sources

Home - About - Disclaimer - Privacy