Results 241 to 250 of about 666,291 (363)
Generative artificial intelligence: a historical perspective. [PDF]
He R, Cao J, Tan T.
europepmc +1 more source
Kuroda and Fujimura Laboratory -Image and Computer Graphics Laboratory-
Takashi Ueno +5 more
openalex +2 more sources
Bridging Nature and Technology: A Perspective on Role of Machine Learning in Bioinspired Ceramics
Machine learning (ML) is revolutionizing the development of bioinspired ceramics. This article investigates how ML can be used to design new ceramic materials with exceptional performance, inspired by the structures found in nature. The research highlights how ML can predict material properties, optimize designs, and create advanced models to unlock a ...
Hamidreza Yazdani Sarvestani +2 more
wiley +1 more source
ErB4 and NdB4 nanostructured powders are produced by mechanochemical synthesis. 5 h mechanical alloying and 4 M HCl acid leaching are used in the production. ErB4 and NdB4 powders exhibit maximum magnetization of 0.4726 emu g−1 accompanied with an antiferromagnetic‐to‐paramagnetic phase transition at about TN = 18 K and 0.132 emu g−1 with a maximum at ...
Burçak Boztemur +5 more
wiley +1 more source
Deep learning-based image analysis in muscle histopathology using photo-realistic synthetic data. [PDF]
Mill L +14 more
europepmc +1 more source
Hydrostatic bearings excel in high‐precision applications, but their performance hinges on a continuous external supply. This study evaluates various material combinations for sliding surfaces to mitigate damage during supply failures or misalignment and to discover the most effective materials identified for enhancing the reliability and efficiency of
Michal Michalec +6 more
wiley +1 more source
BladeSynth: A High-Quality Rendering-Based Synthetic Dataset for Aero Engine Blade Defect Inspection. [PDF]
Mohammed Eltoum MA +4 more
europepmc +1 more source
In this study, the mechanical response of Y‐shaped core sandwich beams under compressive loading is investigated, using deep feed‐forward neural networks (DFNNs) for predictive modeling. The DFNN model accurately captures stress–strain behavior, influenced by design parameters and loading rates.
Ali Khalvandi +4 more
wiley +1 more source

