Results 171 to 180 of about 99,350 (321)

Factorization Machine‐Based Active Learning for Functional Materials Design with Optimal Initial Data

Advanced Intelligent Discovery, EarlyView.
This work investigates the optimal initial data size for surrogate‐based active learning in functional material optimization. Using factorization machine (FM)‐based quadratic unconstrained binary optimization (QUBO) surrogates and averaged piecewise linear regression, we show that adequate initial data accelerates convergence, enhances efficiency, and ...
Seongmin Kim, In‐Saeng Suh
wiley   +1 more source

Accelerating Biosensor Discovery: A Computationally‐Driven Pipeline for Microplastics Monitoring

Advanced Intelligent Discovery, EarlyView.
A computationally guided pipeline unites molecular simulation, synthetic biology, electrochemical engineering, and machine learning to accelerate biosensor discovery. A Bacillus anthracis carbohydrate‐binding module is used to develop a high‐performance micro‐ and nanoplastics sensor with greatly reduced error and variability.
Gabriel X. Pereira, Marcos de C. Leite, Pedro H. M. Zanineli, Juliana N. Y. Costa, Débora M. Cunha, Sophia P. Serra, Pedro H. Sophia, Flávio M. Shimizu, Yasmin W. Moura, Célio C. Oliveira, Gabriel R. Schleder, Gabriela F. Persinoti, Leandro Merces, Renato S. Lima   +13 more
wiley   +1 more source

FIRE‐GNN: Force‐Informed, Relaxed Equivariance Graph Neural Network for Rapid and Accurate Prediction of Surface Properties

Advanced Intelligent Discovery, EarlyView.
This study introduces FIRE‐GNN, a force‐informed, relaxed equivariant graph neural network for predicting surface work functions and cleavage energies from slab structures. By incorporating surface‐normal symmetry breaking and machine learning interatomic potential‐derived force information, the approach achieves state‐of‐the‐art accuracy and enables ...
Circe Hsu, Claire Schlesinger, Karan Mudaliar, Jordan Leung, Robin Walters, Peter Schindler   +5 more
wiley   +1 more source

All possible lightest supersymmetric particles in R-parity violating minimal supergravity models [PDF]

, 2009
Herbi K. Dreiner, S. Grab
openalex   +1 more source

Advancing Efficient Error Reduction in DNA Data Storage Systems with Deep Learning‐Based Denoising Models

Advanced Intelligent Discovery, EarlyView.
Deep learning‐based denoising models are applied to DNA data storage systems to enhance error reduction and data fidelity. By integrating DnCNN with DNA sequence encoding methods, the study demonstrates significant improvements in image quality and correction of substitution errors, revealing a promising path toward robust and efficient DNA‐based ...
Seongjun Seo, Anshula Tandon, Nguyen Kim Uyen, Quoc Nam Le, Jee‐Hyong Lee, Sung Ha Park   +5 more
wiley   +1 more source

Predictive Dirac neutrino spectrum with strong CP solution in SU(5) L × SU(5) R unification

Journal of High Energy Physics
We develop a grand unified theory of matter and forces based on the gauge symmetry SU(5) L × SU(5) R with parity interchanging the two factor groups.
K.S. Babu, Rabindra N. Mohapatra, Anil Thapa   +2 more
doaj   +1 more source

Self‐Driving Laboratory Optimizes the Lower Critical Solution Temperature of Thermoresponsive Polymers

Advanced Intelligent Discovery, EarlyView.
A low‐cost, self‐driving laboratory is developed to democratize autonomous materials discovery. Using this "frugal twin" hardware architecture with Bayesian optimization, the platform rapidly converges to target lower critical solution temperature (LCST) values while self‐correcting from off‐target experiments, demonstrating an accessible route to data‐
Guoyue Xu, Renzheng Zhang, Tengfei Luo
wiley   +1 more source

R-parity violating two-loop level rainbowlike contribution to the fermion electric dipole moment [PDF]

, 2023
Nodoka Yamanaka
openalex   +1 more source

Gaussian Process Regression–Neural Network Hybrid with Optimized Redundant Coordinates: A New Simple Yet Potent Tool for Scientist's Machine Learning Toolbox

Advanced Intelligent Discovery, EarlyView.
A machine learning method, opt‐GPRNN, is presented that combines the advantages of neural networks and kernel regressions. It is based on additive GPR in optimized redundant coordinates and allows building a representation of the target with a small number of terms while avoiding overfitting when the number of terms is larger than optimal.
Sergei Manzhos, Manabu Ihara
wiley   +1 more source