Results 161 to 170 of about 2,251,103 (302)

Polarization Dynamics in Ferroelectrics: Insights Enabled by Machine Learning Molecular Dynamics

Advanced Science, EarlyView.
Machine learning molecular dynamics is presented as a route to capture polarization switching, domain wall kinetics, topological polar textures, and polar mechanical coupling beyond the limits of conventional atomistic methods. This Perspective surveys recent progress and identifies key methodological directions, including long‐range electrostatics ...
Dongyu Bai, Ri He, Junxian Liu, Liangzhi Kou   +3 more
wiley   +1 more source

Direct Regret Optimization in Bayesian Optimization

CoRR
Bayesian optimization (BO) is a powerful paradigm for optimizing expensive black-box functions. Traditional BO methods typically rely on separate hand-crafted acquisition functions and surrogate models for the underlying function, and often operate in a myopic manner.
Fengxue Zhang, Yuxin Chen
openaire   +2 more sources

A Portable Soft Robotic Glove with Fully Functional Thumb Assistance for Complex Dexterous Fine Motor Skills

Advanced Science, EarlyView.
A portable, sensorized, and controlled dexterous thumb‐enhanced glove helps stroke survivors swipe phones, twist caps, and perform other tasks. It is based on a powerful continuously, segmented origami dual chamber actuator to achieve active thumb CMC and MCP joint assistance and passively extend the IP joint.
Disheng Xie, Zhen Wang, Zhongping Ye, Minghao Liu, Xiangqian Shi, Shuk Fan Tong, Jianbin Liu, Chuanbin Mao, Thomas W. Leung, Haitao Liu, Raymond Kai‐yu Tong   +10 more
wiley   +1 more source

Optimal Initialization of Batch Bayesian Optimization

CoRR
Field experiments and computer simulations are effective but time-consuming methods of measuring the quality of engineered systems at different settings. To reduce the total time required, experimenters may employ Bayesian optimization, which is parsimonious with measurements, and take measurements of multiple settings simultaneously, in a batch.
Jiuge Ren, David Sweet
openaire   +2 more sources

Automating Chemical Reasoning in High‐Throughput Phase Identification With a Probabilistic, LLM‐Guided Framework

Advanced Science, EarlyView.
Autonomous laboratories can now synthesize materials faster than experts can interpret the resulting diffraction data. A probabilistic framework combines refinement‐fit metrics with large language model‐derived chemical reasoning to rank competing phase interpretations and flag those unsuitable for autonomous use.
Olympia Dartsi, Lauren N. Walters, Amalie E. Trewartha, Steven B. Torrisi, Amanda Volk, Liam Joyce, Gerbrand Ceder, Anubhav Jain   +7 more
wiley   +1 more source

StackingNet: Collective Inference Across Independent AI Foundation Models

Advanced Science, EarlyView.
ABSTRACT Artificial intelligence (AI) built on large foundation models has transformed language understanding, computer vision, and reasoning, yet these systems remain isolated and cannot readily share their capabilities. Coordinating the complementary strengths of independently developed, black‐box foundation models is essential for trustworthy ...
Siyang Li, Chenhao Liu, Dongrui Wu, Zhigang Zeng, Lieyun Ding   +4 more
wiley   +1 more source

A Closed‐Loop Framework for Inverse Design: Dynamic Training and Intelligent Optimization for Heterostructured Materials

Advanced Science, EarlyView.
To accelerate the inverse design of heterostructured metal matrix composites, a closed‐loop scientific machine learning framework integrates continual learning prediction with NSGA‐II‐PMCP optimization. The framework maps microstructural descriptors to strength, toughness, and modulus, expands high‐quality Pareto solutions, and guides experimentally ...
Zhiyan Zhong, Xueru Zheng, Xiao Zhou, Zhengheng Tao, Wan Han, Jingyi Pan, Dian Wu, Ning Gao, Lei Liu, Zhongyang Wang, Fanchao Meng, Tongxiang Fan   +11 more
wiley   +1 more source

Automation and Active Learning for the Multi‐Objective Optimization of Antibody Formulations

Advanced Science, EarlyView.
Successful antibody formulation necessitates balancing factors such as thermal stability, colloidal stability, and viscosity across a vast excipient design space. This work integrates robotic liquid handling, high‐throughput biophysical characterization, and multi‐objective Bayesian optimization in an iterative closed‐loop Design‐Build‐Test‐Learn cycle.
D. Christopher Radford, Matthew Tamasi, Elena Di Mare, Adam J. Gormley   +3 more
wiley   +1 more source

Bayesian Portfolio Selection with Gaussian Mixture Returns [PDF]

Markowitz portfolio selection is challenged by huge implementation barriers. This paper addresses the parameter uncertainty and deviation from normality in a Bayesian framework. The non-normal asset returns are modeled as finite Gaussian mixtures.
Qian, Hang
core  

A Global Methane Observation System to Reduce Uncertainty for Anthropogenic and Natural Sources and Sinks for Detecting and Attributing Climate Feedbacks

Advanced Science, EarlyView.
Conceptual illustration of a Global Ecosystem Methane Observing System (GEM‐OS) integrating satellites, aircraft, atmospheric networks, and ecosystem measurements to quantify methane emissions from anthropogenic and natural sources. The multi‐scale observing framework improves source attribution, reduces uncertainty in regional methane budgets, and ...
P. Ciais, S. Peng, J. Chang, F. Li, Q. Zhu, K. Yuan, G. Hugelius, H. Li, Y. Cai, F. Chevallier, K. Tibrewal, E. A. Kort, K. Arndt, J. Watts, B. Buma, N. Besic, P. I. Palmer, H. Cadillo‐Quiroz, E. Euskirchen, M. J. Gondwe, A. Hoyt, R. Jackson, S. Malone, D. Monteverde, S. Natali, M. Ramonet, C. Rey‐Sanchez, L. B. Sagang, E. A. G. Schuur, R. Vargas, R. Varner, Z. Zhang, B. Poulter   +32 more
wiley   +1 more source