Results 131 to 140 of about 405,787 (272)

XGBoost-Enhanced Graph Neural Networks: A New Architecture for Heterogeneous Tabular Data

Applied Sciences
Graph neural networks (GNNs) perform well in text analysis tasks. Their unique structure allows them to capture complex patterns and dependencies in text, making them ideal for processing natural language tasks. At the same time, XGBoost (version 1.6.2.)
Liuxi Yan, Yaoqun Xu
doaj   +1 more source

Artificial Intelligence‐Assisted Workflow for Transmission Electron Microscopy: From Data Analysis Automation to Materials Knowledge Unveiling

Advanced Materials, EarlyView.
AI‐Assisted Workflow for (Scanning) Transmission Electron Microscopy: From Data Analysis Automation to Materials Knowledge Unveiling. Abstract (Scanning) transmission electron microscopy ((S)TEM) has significantly advanced materials science but faces challenges in correlating precise atomic structure information with the functional properties of ...
Marc Botifoll, Ivan Pinto‐Huguet, Enzo Rotunno, Thomas Galvani, Catalina Coll, Payam Habibzadeh Kavkani, Maria Chiara Spadaro, Yann‐Michel Niquet, Martin Børstad Eriksen, Sara Martí‐Sánchez, Georgios Katsaros, Giordano Scappucci, Peter Krogstrup, Giovanni Isella, Andreu Cabot, Gonzalo Merino, Pablo Ordejón, Stephan Roche, Vincenzo Grillo, Jordi Arbiol   +19 more
wiley   +1 more source

Non-convolutional graph neural networks.

Advances in Neural Information Processing Systems 37
Rethink convolution-based graph neural networks (GNN) -- they characteristically suffer from limited expressiveness, over-smoothing, and over-squashing, and require specialized sparse kernels for efficient computation. Here, we design a simple graph learning module entirely free of convolution operators, coined random walk with unifying memory (RUM ...
Wang, Yuanqing, Cho, Kyunghyun
openaire   +2 more sources

Engineered Protein‐Based Ionic Conductors for Sustainable Energy Storage Applications

Advanced Materials, EarlyView.
Rational incorporation of charged residues into an engineered, self‐assembling protein scaffold yields solid‐state protein films with outstanding ionic conductivity. Salt‐doping further enhances conductivity, an effect amplified in the engineered variants. These properties enable the material integration into an efficient supercapacitor.
Juan David Cortés‐Ossa, Paolo Blesio, Marcial Fernandez‐Castro, Lisa Almonte, Maxence Fernandez, Mantas Liutkus, Perumal Pandurangan, Carlos Sabater, Aitor Villaverde, Manuel Melle‐Franco, Nurit Ashkenasy, Felipe Jiménez‐Ángeles, M. Carmen Morant‐Miñana, M. Reyes Calvo, Aitziber L. Cortajarena   +14 more
wiley   +1 more source

Beyond Presumptions: Toward Mechanistic Clarity in Metal‐Free Carbon Catalysts for Electrochemical H2O2 Production via Data Science

Advanced Materials, EarlyView.
Metal‐free carbon catalysts enable the sustainable synthesis of hydrogen peroxide via two‐electron oxygen reduction; however, active site complexity continues to hinder reliable interpretation. This review critiques correlation‐based approaches and highlights the importance of orthogonal experimental designs, standardized catalyst passports ...
Dayu Zhu, Hsi‐wen Wu, Xiao Wang, Jie Zhang   +3 more
wiley   +1 more source

Light‐Induced Entropy for Secure Vision

Advanced Materials, EarlyView.
This work realized a ternary true random number generator by exploiting stochastic traps emerging within multiple junction interfaces, and quantitatively validated the generation of high‐quality random numbers. Furthermore, it successfully demonstrated diverse applications, including AI‐resilient image security, thereby providing a valuable guide for ...
Juhyung Seo, Seungme Kang, Chaehyun Kim, Taehyun Park, Youngwoo Yoo, Yeong Kwon Kim, Wonjun Shin, Byung Chul Jang, Young‐Joon Kim, Hocheon Yoo   +9 more
wiley   +1 more source

Science‐Towards‐Technology Breakthrough in CO2 Electroreduction: Multiphysics, Multiscale, and Artificial Intelligence Insights

Advanced Materials, EarlyView.
Electrochemical CO2RR is a key technology for converting CO2 into chemicals, but there remains a gap between “laboratory science” and “engineering practice” in current research. This review establishes a multi‐scale research framework, encompassing atomic‐level characterization, microenvironment regulation, external field‐assisted optimization, and AI ...
Ping Hong, Changfan Xu, Huaping Zhao, Yong Lei   +3 more
wiley   +1 more source

Self‐Assembled Monolayers in p–i–n Perovskite Solar Cells: Molecular Design, Interfacial Engineering, and Machine Learning–Accelerated Material Discovery

Advanced Materials, EarlyView.
This review highlights the role of self‐assembled monolayers (SAMs) in perovskite solar cells, covering molecular engineering, multifunctional interface regulation, machine learning (ML) accelerated discovery, advanced device architectures, and pathways toward scalable fabrication and commercialization for high‐efficiency and stable single‐junction and
Asmat Ullah, Ying Luo, Stefaan De Wolf
wiley   +1 more source

Two‐Way Shape Memory Polymer Composite Gripper for Adaptive Robotic Applications

Advanced Materials Technologies, EarlyView.
A two‐way shape memory polymer (SMP) composite is developed with intrinsic shape‐changing capability driven solely by temperature, eliminating external actuation loads. Embedding the SMP in a low‐stiffness elastomeric matrix enabled reversible transformations during heating and cooling cycles.
Aamna Hameed, Kamran Ahmed Khan
wiley   +1 more source

Conformal inductive graph neural networks

Conformal prediction (CP) transforms any model's output into prediction sets guaranteed to include (cover) the true label. CP requires exchangeability, a relaxation of the i.i.d. assumption, to obtain a valid distribution-free coverage guarantee. This makes it directly applicable to transductive node-classification.
Zargarbashi, Soroush H., Bojchevski, Aleksandar   +1 more
openaire   +2 more sources