Results 111 to 120 of about 13,204,286 (295)

Reconciling grokking with statistical learning theory through the lens of norm- and stability-based generalization bounds

Neurocomputing
In recent years, Artificial Intelligence, particularly Machine Learning, has achieved remarkable success in solving complex problems. However, this progress has also revealed the emergence of unexpected, poorly understood, and elusive phenomena that characterize the behavior of machine intelligence and learning processes.
Luca Oneto, Sandro Ridella, Simone Minisi, Andrea Coraddu, Davide Anguita   +4 more
openaire   +1 more source

Symmetry‐Guided Multifunctional Acoustic System Based on Mechanically Actuated Sonic Crystals

Advanced Engineering Materials, EarlyView.
This study presents the design, simulation, and experimental validation of amultifunctional acoustic metamaterial based on rotationally engineered sonic crystals.By tuning cylinder orientations, controllable band gaps and six distinct functionalities—including switching, topological insulation, beam splitting, and logic operations—areachieved ...
Yuanyan Zhao, Sriram Subramanian, Gianluca Memoli   +2 more
wiley   +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

Design of Dual-Motor Drive Composite Control Strategy Based on Iterative Learning Feedforward Control and Super-Twisting Sliding Mode Observer

Actuators
Periodic and non-periodic disturbances significantly affect the tracking accuracy of servo systems. A dual-motor drive composite control strategy based on iterative learning feedforward control and super-twisting sliding mode observer is proposed ...
Anning Wang, Xianying Feng, Hao Wang, Ming Yao   +3 more
doaj   +1 more source

Stability Theory of Universal Learning Network

IEEJ Transactions on Electronics, Information and Systems, 1996
Kotaro Hirasawa, Masanao Obayashi, Masaru Koga   +2 more
openaire   +2 more sources

Does Central Bank Transparency Matter for Economic Stability [PDF]

This paper studies the impact of monetary policy transparency on economic stability, when economic agents are boundedly rational. I first consider a simple class of microfunded general equilibrium models with nominal rigidities and learning.
Stefano Eusepi
core  

Noah's dove returns: Armenia, Turkey and the debate on genocide / European Stability Initiative

, 2009
Parallel als Buch-Ausg ...
unknown
core   +1 more source

Modeling Dislocation Cutting of γ′ Precipitates in Ni‐Base Superalloys: Linking Atomistic and Dislocation Dynamics Simulations

Advanced Engineering Materials, EarlyView.
Dislocation cutting of γ′ precipitates in Ni‐based superalloys is investigated by linking atomistic simulations with discrete dislocation dynamics. The critical cutting stress is shown to be governed by the antiphase boundary energy, while line tension effects promote edge‐preferred cutting.
Frédéric Houllé, Siwen Gao, Marc Fivel, Anxin Ma, Daria Smirnova, Sriram Anand, Arun Prakash, Julien Guénolé, Alexander Hartmaier, Erik Bitzek   +9 more
wiley   +1 more source

Adaptive hybrid function projective synchronization of chaotic systems with fully unknown periodical time-varying parameters

Nonlinear Analysis, 2019
In this paper, an adaptive learning control approach is presented for the hybrid functional projective synchronization (HFPS) of different chaotic systems with fully unknown periodical time-varying parameters.
Jinsheng Xing
doaj  

Machine Learning‐Supported Analysis for Predicting and Visualizing Nonlinear Relationships Between Material Properties in Electroplated Chromium Layers

Advanced Engineering Materials, EarlyView.
This study applies machine learning regression to predict chromium layer thickness in decorative trivalent chromium electroplating, using 441 experiments from laboratory‐scale (1L) and pilot‐scale (14L) setups. Tree‐based models, particularly CatBoost, outperformed linear regression by capturing nonlinear parameter interactions (R2$R^2$ up to 0.77 ...
Christoph Baumer, Christopher Mai, Luca Eisentraut, Andreas Bund, Ricardo Buettner   +4 more
wiley   +1 more source