Results 101 to 110 of about 7,211,078 (250)

Current Status and Challenges in Data Collection for Aerospace Coatings Deposited by Plasma Spraying

Advanced Engineering Materials, EarlyView.
An innovative approach has been integrated into the GRENAT project to optimize plasma spraying and coating performance. Raw materials are accelerated and melted in the plasma generated by torches, creating coatings. Monitoring sensors collect process data which are combined with ex situ characterization data.
Lila Randriamananjara, Vincent Rat, Quentin Dubreuil, Patrice Valorge, Simon Goutier, Alain Denoirjean, Olivier Messe, Céline Ruelle, Jean‐Philippe Poli   +8 more
wiley   +1 more source

Coherent Optical OFDM Modem Employing Artificial Neural Networks for Dispersion and Nonlinearity Compensation in a Long-Haul Transmission System [PDF]

In order to satisfy the ever increasing demand for the bandwidth requirement in broadband services the optical orthogonal frequency division multiplexing (OOFDM) scheme is being considered as a promising technique for future high-capacity optical ...
Jarajreh, Mutsam Abdel-karim
core  

An exact mapping from ReLU networks to spiking neural networks

, 2023
Deep spiking neural networks (SNNs) offer the promise of low-power artificial intelligence. However, training deep SNNs from scratch or converting deep artificial neural networks to SNNs without loss of performance has been a challenge.
Wulfram Gerstner, Ana Stanojevic, Cherubini, Giovanni, Stanisław Woźniak, Bellec, Guillaume, Pantazi, Angeliki, Angeliki Pantazi, Giovanni Cherubini, Woźniak, Stanisław, Guillaume Bellec, Gerstner, Wulfram, Stanojevic, Ana   +11 more
core   +1 more source

Microstructure Reconstruction in Battery Electrodes Using Machine Learning Based on Low‐Voltage Focused Ion Beam–Scanning Electron Microscopy Tomography Images

Advanced Engineering Materials, EarlyView.
Low‐voltage FIB‐SEM tomography combined with a image preprocessing pipeline improves phase contrast and enables reliable machine‐learning segmentation of conductive networks in lithium‐ion battery electrodes. Structural descriptors are extracted from segmented images, done semimanually and automated, and compared.
Lisa Beran, Vincent Nebel, Dominik Perius, Kshitij Kumar, Yannis Heim, Laura Bies, Tobias Kraus   +6 more
wiley   +1 more source

Studying the capacity of cellular encoding to generate feedforward neural network topologies [PDF]

, 2004
Proceeding of: IEEE International Joint Conference on Neural Networks, IJCNN 2004, Budapest, 25-29 July 2004Many methods to codify artificial neural networks have been developed to avoid the disadvantages of direct encoding schema, improving the search ...
Gutiérrez Sánchez, Germán, Galván, Inés M., Molina, José M., Sanchis de Miguel, María Araceli   +3 more
core   +1 more source

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, Cesar Alvarez‐Llamas, Vincent Motto‐Ros, Christophe Dujardin, Jérémie Margueritat, David Rodney   +5 more
wiley   +1 more source

Passive all-optical nonlinear neuron activation via PPLN nanophotonic waveguides

eLight
Artificial intelligence (AI) is transforming modern life, yet the growing scale of AI applications places mounting demands on computational resources, raising sustainability concerns.
Wujie Fu, Xiaodong Shi, Sakthi Sanjeev Mohanraj, Lei Shi, Yuan Gao, Zexian Wang, Jianing Wang, Xu Chen, Luo Qi, Pragati Aashna, Guanyu Chen, Di Zhu, Aaron Danner   +12 more
doaj   +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, Lateef Abdul, Stephan Barth, Martin Glauer, Manuel Günther, Fabian Neuhaus, Jan‐Ole Perschewski, Thomas Bjarsch, Henrik Abel, Johannes Bosch, Niklas Meyer, Peter Hofmann, Marc Drechsler, Alexander Dyck, Dhanunjaya Kumar Nerella, Marvin Tegeler, Oleg Shchyglo, Ingo Steinbach, Timo Klecker, Henk Birkholz, Ehsan Borzabadi Farahani, Bernard Fedelich, Cetin Haftaoglu, Tarakeshwar Lakshmipathy, Elena Garcia Trelles, Christoph Schweizer, Reza Darvishi Kamachali, Lukas Koschmieder, Janin Eiken, Markus Apel, Sung‐Min Wi, Jiangdong Zhao, Andreas Fezer, Nicolas Christ, Patrick Schneider, Eldor Urinov, Veit Königer, Volker Knoblauch, Janik Harter, Thomas Seifert, Thitichai Janpheng, Florian Fuchs, Fabian Teichert, Jörg Schuster, Anke Bardehle, Andreas Limper, Ulrich Giese, Carlos Lucke, Mario Beiner, Christoph Gögelein, Lisa Leuchtenberger‐Engel, Christian Hopmann, Felix Wentzien, Heike Wittek, Benjamin Klie, Alexander Röhrs, Ludger Overmeyer, Achraf Atila, Marcel Sadowski, Leopold Talirz, Jan Janssen, Jesper R. Pedersen, Peter Beck, Tejs Vegge, Ivano E. Castelli, Wolfgang Wenzel, Tilmann Hickel, Jörg Schaarschmidt   +67 more
wiley   +1 more source

Matrix neural networks

, 2017
Traditional neural networks assume vectorial inputs as the network is arranged as layers of single line of computing units called neurons. This special structure requires the non-vectorial inputs such as matrices to be converted into vectors.
Junbin Gao, Guo, Yi (R18457), Yi Guo, Wang, Zhiyong, Zhiyong Wang, Gao, Junbin   +5 more
core   +1 more source

Realization of All-Optical Nonlinear Activation Function in Photonic Nano-Beam Resonators for Application in Optical Neural Networks

IEEE Photonics Journal
This study presents the development of a novel nonlinear activation function (NLAF) for integrated optical neural networks (ONNs), leveraging a thermally actuated photonic crystal (PC) nanobeam resonator (PCNBR) integrated with a phase-change material ...
Samaneh Amiri, Mehdi Miri
doaj   +1 more source