Results 161 to 170 of about 262,580 (281)
Robust Partial Multi‐Label Learning Under Dual Noise via Joint Subspace Learning
ABSTRACT Partial Multi‐label Learning (PML) deals with the ambiguity where each instance is annotated with a set of candidate labels, and only a subset of which is valid. While existing PML methods focus primarily on label disambiguation, they often rely on the assumption of a clean feature space.
Yuanjian Zhang +4 more
wiley +1 more source
Research on AUV Underwater Localization Method Based on an n-Shaped Array. [PDF]
Han C, Gao M, Shen T, Guo C.
europepmc +1 more source
Vertical Deformation Mapping: Steering Optimiser Toward Flat Minima
ABSTRACT Standard deep learning optimisation is typically conducted on shape‐fixed loss surfaces. However, shape‐fixed loss surfaces may impede optimisers from reaching flat regions closely associated with strong generalisation. In this work, we propose a new paradigm named deformation mapping to deform the loss surface during optimisation.
Liangming Chen +4 more
wiley +1 more source
ABSTRACT A reduced‐order model (ROM) for the temperature field based on time‐space proper orthogonal decomposition (POD) is presented to improve the computational efficiency of transient temperature rise in oil‐immersed power transformers with a complete oil natural convection cooling loop.
Haijuan Lan +5 more
wiley +1 more source
Rosette Cardiac MR Fingerprinting for Simultaneous T<sub>1</sub>, T<sub>2</sub>, T 2 * , and Fat Fraction Mapping Using a Multi-Echo Deep Image Prior Reconstruction. [PDF]
Cummings E +5 more
europepmc +1 more source
ABSTRACT Structural mechanics field simulation plays a critical role in the vibration characteristic analysis of electrical equipment. Existing structural field analysis of equipment based on numerical simulation faces challenges such as convergence difficulties and prolonged computational time, failing to meet the demand for real‐time prediction of ...
Wanqing Wang +6 more
wiley +1 more source
ABSTRACT Diagnosing high‐impedance ground faults (HIGFs) in distribution networks is extremely challenging because high transition resistance significantly reduces electrical signal strength and unpredictable initial fault phase angles coupled with asymmetric voltage disturbances often lead to misclassification.
Zhengyang Li +5 more
wiley +1 more source
Domain-specific schema reuse supports flexible learning to learn in the primate brain. [PDF]
Tian K +7 more
europepmc +1 more source
Multi-target passive positioning with signal classification and MIMO radar. [PDF]
Wang H, Liu X, Lei Z.
europepmc +1 more source

