Results 81 to 90 of about 8,736,022 (255)
A Practical Noise2Noise Denoising Pipeline for High‐Throughput Raman Spectroscopy
Advanced Engineering Materials, EarlyView.A lightweight and reproducible denoising pipeline for high‐throughput Raman spectroscopy is introduced, based on a 1D convolutional autoencoder trained with a Noise2Noise strategy. Using only repeated short‐exposure acquisitions, the method suppresses stochastic noise without reference spectra, enabling reliable spectral reconstruction while preserving
David Martin‐Calle +5 more
wiley +1 more source
New AI‐Assisted Approach for Expanding the Solution Space: Application to Lattice Structure Design
Advanced Engineering Materials, EarlyView.This work introduces an innovative framework for designing structured materials by ex panding the design space through reparameterization of qualitative variables into continuous structural descriptors. Combined with machine‐learning‐based prediction and multi‐objective optimization, the approach enables the discovery of novel lattice architectures ...
G. H. Gahimbare +5 more
wiley +1 more source
Advanced Engineering Materials, EarlyView.The OntOMat ontology establishes a structured framework for polymer matrix fiber reinforced composite materials, integrating manufacturing processes, characterization methods, and multiscale design through the VDI/VDE 3682 formalized process description standard.
Nicolas Christ +19 more
wiley +1 more source
Advanced Engineering Materials, EarlyView.Binder‐free laser powder bed fusion of 8YSZ with a femtosecond laser is used to map process windows linking scan strategy, heat accumulation, and grain growth. Time‐resolved thermography and simulations reveal thermal regimes that enable continuous, vitrified, and fine‐grained 8YSZ surface layers without absorptive additives and demonstrate ...
Markus Kühn +5 more
wiley +1 more source
Heterophily-informed Message Passing
Publisher Copyright: © 2025, Transactions on Machine Learning Research. All rights reserved.Graph neural networks (GNNs) are known to be vulnerable to oversmoothing due to their implicit homophily assumption.
Solin, Arno, Garg, Vikas, Wang, Haishan
core
Frontiers of Statistics and Machine Learning
Oberwolfach ReportsAI is currently the central theme in science. Whereas the underlying algorithms rely on rather simple mathematical operations such as matrix-vector multiplications and applying non-linearities componentwise, deriving a theoretical understanding proves to be extremely challenging.
Marc Hoffmann +3 more
openaire +2 more sources
Investigating the Low‐Temperature Phase Stability of the Binary Ta–W System
Advanced Engineering Materials, EarlyView.Atomistic simulations show that the binary Ta–W system forms ordered intermetallic phases, B2‐TaW and D03‐TaW3, as 0 K ground states. Configurational entropy, however, lowers the free energy of the disordered bcc solid solution, which becomes the stable phase above about 400 K.
Klemens Lechner +7 more
wiley +1 more source
Supporting AI Readiness Through Digital Workflows in Materials Science
Advanced Engineering Materials, EarlyView.Digitalization drives innovation in materials science by connecting data silos and turning heterogeneous processes into reusable research pipelines. Across 13 MaterialDigital projects, digital workflows reveal complementary pathways toward AI‐ready materials research, founded on structured data, persistent artifacts, executable orchestration, and ...
Marian Bruns +67 more
wiley +1 more source
A Multi‐Scale Machine Learning Framework for the Inverse Design of High Entropy Alloys
Advanced Engineering Materials, EarlyView.High‐entropy alloys offer vast potential for various applications, including electrocatalysis; however, their compositional complexity challenges conventional screening. We introduce an inverse‐design framework combining two neural networks to determine optimal compositions and reconstruct nanoparticle geometry from targeted properties and conventional
Mikael Takoutsin +14 more
wiley +1 more source
Position: topological deep learning is the new frontier for relational learning
Topological deep learning (TDL) is a rapidly evolving field that uses topological features to understand and design deep learning models. This paper posits that TDL is the new frontier for relational learning.
Nasrin, F +21 more
core