Results 151 to 160 of about 1,925,652 (255)

Physics‐Informed Machine Learning for Sustainable Alloy Design: Toward a Recyclable Unified Q&P Steel

Advanced Science, EarlyView.
A physics‐informed property‐bridging framework links high‐throughput hardness screening to tensile performance in quenching and partitioning steels. By transferring metallurgically guided representations across properties, a single alloy composition is designed to achieve multiple strength grades through heat‐treatment tuning alone, offering a ...
Xiaolu Wei, Yong Li, Chenchong Wang, Lingyu Wang, Xiang Song, Keming Mao, Yu Zhang, Wei Xu   +7 more
wiley   +1 more source

Interpretable Machine Learning Framework for Nb─Si Based Alloy Design with Enhanced Fracture Toughness

Advanced Science, EarlyView.
An interpretable machine learning framework integrating SHAP and PDP analysis identifies critical design descriptors from 139 physicochemical features for Nb─Si alloys. The framework achieves <7% prediction error and guides the discovery of Nb38.5Ti38.5Si3Zr18V2 alloy with 22.791 MPa·m1/2 fracture toughness, breaking the 20 MPa·m1/2 barrier.
Dezhi Chen, Chao Xu, Jingyue Yu, Qi Wang, Hongze Fang, Shuo Yin, Turab Lookman, Ruirun Chen   +7 more
wiley   +1 more source

Hyperparameter Optimization EM Algorithm via Bayesian Optimization and Relative Entropy

Entropy
Hyperparameter optimization (HPO), which is also called hyperparameter tuning, is a vital component of developing machine learning models. These parameters, which regulate the behavior of the machine learning algorithm and cannot be directly learned from
Dawei Zou, Chunhua Ma, Peng Wang, Yanqiu Geng   +3 more
doaj   +1 more source

Machine Learning‐Assisted KCl‐CaCl2‐LiCl Electrolyte Design for Low‐Temperature, High‐Performance Calcium‐Based Liquid Metal Batteries

Advanced Science, EarlyView.
A machine learning‐assisted framework optimizes the KCl‐CaCl2‐LiCl ternary electrolyte. The optimized 13:35:52 mol% composition enables Ca‐based liquid metal batteries to operate stably at 480 °C, with >99.5% coulombic efficiency, ultralow self‐discharge, and excellent cycling stability, advancing low‐temperature large‐scale energy storage.
Xinglin Zhou, Lei Huang, Yan Zhou, Xiaohui Ning   +3 more
wiley   +1 more source

Research on parameter selection and optimization of C4.5 algorithm based on algorithm applicability knowledge base

Scientific Reports
Given that the decision tree C4.5 algorithm has outstanding performance in prediction accuracy on medical datasets and is highly interpretable, this paper carries out an optimization study on the selection of hyperparameters of the algorithm in order to ...
Yiyan Zhang, Yi Xin, Qin Li
doaj   +1 more source

A Versatile‐Designable Framework for Active and Programmable Shape‐Morphing Soft Matter Systems: From Inverse Design to Closed‐Loop Control

Advanced Science, EarlyView.
A versatile framework integrates addressable electrothermal actuation and strain‐constraint mechanisms to construct programmable shape‐morphing soft matter systems. By combining an analytical inverse design strategy for high‐fidelity 3D surface reconstruction with deep learning‐based closed‐loop control, this approach enables zero‐energy shape locking,
Kai Liu, Peiling Xie, Ruitong Song, Banghan Liu, Rui Guo, Jiu‐an Lv   +5 more
wiley   +1 more source

On Optimizing Hyperparameters for Quantum Neural Networks

2024 IEEE International Conference on Quantum Computing and Engineering (QCE)
The increasing capabilities of Machine Learning (ML) models go hand in hand with an immense amount of data and computational power required for training. Therefore, training is usually outsourced into HPC facilities, where we have started to experience limits in scaling conventional HPC hardware, as theorized by Moore's law.
Sabrina Herbst, Vincenzo De Maio, Ivona Brandic   +2 more
openaire   +2 more sources

A Generative Neuro‐Symbolic AI for Protein Sequence Design

Advanced Science, EarlyView.
We introduce EffieDes, a neuro‐symbolic framework coupling deep learning‐based fitness landscape parameterization with exact automated reasoning. Unlike greedy sampling, EffieDes identifies sequences that globally optimize fitness while satisfying intricate design constraints.
Marianne Defresne, Delphine Dessaux, Samuel Buchet, Lucie Barthe, Liza Ammar‐Khodja, Bessam Azizi, Valentin Durante, Gianluca Cioci, Simon de Givry, Alain Roussel, Luis F. Garcia‐Alles, Thomas Schiex, Sophie Barbe   +12 more
wiley   +1 more source

Models’ hyperparameters: Machine learning models parametrized using random search optimization algorithm of 20 different parameter settings with a 5-fold cross validation to maximize the C-index.

Models’ hyperparameters: Machine learning models parametrized using random search optimization algorithm of 20 different parameter settings with a 5-fold cross validation to maximize the C-index.
Ahmed R. Alsuwaidi (5638088), Taleb M. Almansoori (11702072), Hiba Alblooshi (8386071), Aamna AlShehhi (15877357)   +3 more
core   +1 more source

Multitask Deep Learning Model for Predicting Lymph Node Metastasis and Disease‐Free Survival From Cytology Images in Bladder Cancer: A Multicenter Study With Pan‐Cytology Validation

Advanced Science, EarlyView.
Through self‐supervised pretraining and supervised fine‐tuning on large‐scale cytology image datasets, CytoNet predicts lymph node metastasis and survival. Across independent cohorts, this multitask framework demonstrates robust performance, improves risk stratification beyond radiological assessment, and provides interpretable evidence to support ...
Guibin Hong, Fan Jiang, Ye Xie, Xiaowei Huang, Runnan Shen, Yun Wang, Mengyi Zhu, Haoxuan Wang, Hongkun Yang, Yanxiao Nie, Zhen Lin, Rui Chen, Nengtai Ouyang, Tianxin Lin, Shaoxu Wu   +14 more
wiley   +1 more source