Results 131 to 140 of about 2,854,398 (286)

Symbolic regression as a feature engineering method for machine and deep learning regression tasks

Machine Learning: Science and Technology
In the realm of machine and deep learning (DL) regression tasks, the role of effective feature engineering (FE) is pivotal in enhancing model performance. Traditional approaches of FE often rely on domain expertise to manually design features for machine
Assaf Shmuel, Oren Glickman, Teddy Lazebnik   +2 more
doaj   +1 more source

Sustainable Materials Design With Multi‐Modal Artificial Intelligence

Advanced Science, EarlyView.
Critical mineral scarcity, high embodied carbon, and persistent pollution from materials processing intensify the need for sustainable materials design. This review frames the problem as multi‐objective optimization under heterogeneous, high‐dimensional evidence and highlights multi‐modal AI as an enabling pathway.
Tianyi Xu, Tianshuo Wei, Yan Ge, Bo Peng, Yue Li, Maolin Wang, Peng Wen, Chao Yang, Ye Wei   +8 more
wiley   +1 more source

Integrating Machine Learning With Constant‐Potential Simulation to Unravel Charge‐Transfer Mechanisms in Electrochemical Nitrogen Fixation

Advanced Science, EarlyView.
Integrating interpretable machine learning with the fixed‐potential method reveals a novel mechanism: the catalytic activity of the electrochemical nitrogen reduction reaction is governed by partial charge transfer, induced by variations in the intermediate potential of zero charge under constant potential.
Yufei Xue, Dushuo Feng, Yuefei Zhang, Yang Zhang, Yalong Jiao, Aijun Du, Guoping Gao   +6 more
wiley   +1 more source

Unifying Composition and Process Design: A Heterogeneous Graph Neural Network for Discovering High‐Performance Cu Alloys

Advanced Science, EarlyView.
By overcoming the fixed‐path limitations of conventional machine learning, a heterogeneous graph neural network fundamentally reconstructs material data representation. Integrating variable processing sequences with intrinsic elemental features, this framework enables exploratory optimization across high‐dimensional spaces.
Jie Yin, Qian Lei, Wei Yan, Yue Li, Tong Xie, Shuang Zhou, Chong Wang, Bram Hoex, Qiang Long, Caoyang Jiang, Min Song, Zhou Li, Zhangwei Wang   +12 more
wiley   +1 more source

High‐Throughput Data Generation and Transfer Learning Enabled Microstructure‐Property Integrated Design of Nickel‐Based Powder Metallurgy Superalloy

Advanced Science, EarlyView.
An integrated transfer learning framework integrates CALPHAD simulations, diffusion‐multiple experiments, and literature data to predict long‐term microstructural stability and short‐term mechanical properties of Ni‐based powder metallurgy superalloys. Based on these model predictions, a high‐performance, low‐density alloy, USTB‐PM750, is designed from
Zixin Li, Hongtao Zhang, Zichao Peng, Yuheng Zhang, Qian Lv, Yihuan Cao, Xuqing Wang, Huadong Fu, Jianxin Xie   +8 more
wiley   +1 more source

High‐Throughput Screening and Interpretable Machine Learning for Rational Design of Bimetallic Catalysts for Methane Activation

Advanced Science, EarlyView.
ABSTRACT Methane's efficient catalytic removal is vital for sustainable development. Bimetallic catalysts, though promising for methane activation, pose a design challenge due to their complex compositional space. This work introduces an integrated framework that combines high‐throughput density functional theory (DFT) and interpretable machine ...
Mingzhang Pan, Tian Zhang, Jiawei Dong, Yubao Xie, Kaifeng Zhong, Wei Guan, Haiqiao Wei, Changcheng Fu, Yaqiong Su   +8 more
wiley   +1 more source

SPINEX_ Symbolic Regression: Similarity-based Symbolic Regression with Explainable Neighbors Exploration

CoRR
This article introduces a new symbolic regression algorithm based on the SPINEX (Similarity-based Predictions with Explainable Neighbors Exploration) family. This new algorithm (SPINEX_SymbolicRegression) adopts a similarity-based approach to identifying high-merit expressions that satisfy accuracy- and structural similarity metrics.
M. Z. Naser, Ahmed Naser
openaire   +3 more sources

Early Retinal UCHL1 Dysregulation Coupled With Synaptic Loss Reflects Alzheimer's Disease Severity

Advanced Science, EarlyView.
This study identifies synapse‐enriched deubiquitinase UCHL1 as an early Aβ‐responsive regulator of retinal synaptopathy in Alzheimer's disease. Retinal UCHL1 loss accompanies excitatory synapse degeneration, p75NTR activation, and neuroinflammation, and predicts Braak stage and cognitive decline. Aβ42 fibrils trigger synaptic and UCHL1 depletion before
Altan Rentsendorj, Jean‐Philippe Vit, Alexandre Hutton, Yosef Koronyo, Saba Shahin, Edward Robinson, Ernesto Barron, Anthony Rodriguez, Ousman Jallow, Julia Sheyn, Bhakta Prasad Gaire, Lalita Subedi, Miyah R. Davis, Barathan Gnanabharathi, Alexander V. Ljubimov, Stuart L. Graham, Vivek K. Gupta, Mehdi Mirzaei, Debra Hawes, Katlin Silm, Keith L. Black, Lon S. Schneider, Alfredo A. Sadun, Jesse G. Meyer, Dieu‐Trang Fuchs, Maya Koronyo‐Hamaoui   +25 more
wiley   +1 more source

Fast Symbolic Regression Benchmarking

Symbolic regression (SR) uncovers mathematical models from data. Several benchmarks have been proposed to compare the performance of SR algorithms. However, existing ground-truth rediscovery benchmarks overemphasize the recovery of "the one" expression form or rely solely on computer algebra systems (such as SymPy) to assess success.
openaire   +4 more sources

SymbolNet: neural symbolic regression with adaptive dynamic pruning for compression

Machine Learning: Science and Technology
Compact symbolic expressions have been shown to be more efficient than neural network (NN) models in terms of resource consumption and inference speed when implemented on custom hardware such as field-programmable gate arrays (FPGAs), while maintaining ...
Ho Fung Tsoi, Vladimir Loncar, Sridhara Dasu, Philip Harris   +3 more
doaj   +1 more source