Results 211 to 220 of about 62,374 (308)
Enhancing Generalisation via Cascaded Inertia SGD With Learnt Hyperparameters
ABSTRACT A central challenge in deep learning lies in achieving strong model generalisation, an area in which conventional optimisers such as stochastic gradient descent (SGD) often exhibit limitations, even though they ensure convergence. This paper introduces cascaded inertia SGD (CISGD), a novel optimisation algorithm specifically designed to ...
Yongji Guan +3 more
wiley +1 more source
Fractional dynamics and optical soliton propagation in mono-mode fibers via the Fokas system. [PDF]
Iqbal N +5 more
europepmc +1 more source
ABSTRACT Generalisation is a crucial aspect of deep learning, enabling models to perform well on unseen data. Currently, most optimisers that improve generalisation typically suffer from efficiency bottlenecks. This paper proposes a double‐integration‐enhanced stochastic gradient descent (DIESGD) optimiser, which treats the negative gradient as an ...
Ting Li +3 more
wiley +1 more source
ABSTRACT This paper proposes a boundary control method for nonlinear distributed parameter systems (DPSs) with limited boundary measurements (BMs), as typically encountered in networked cyber‐physical processes with spatially distributed dynamics such as thermal and biomedical diffusion systems.
Yanlin Li +5 more
wiley +1 more source
Dynamical analysis and soliton solutions to (3+1)-dimensional extended quantum nonlinear Zakharov-Kuznetsov equation. [PDF]
Fatima M +6 more
europepmc +1 more source
Development of ± 550 kV DC GIS Basin Insulator
ABSTRACT The basin insulator is a core component of the insulation system for ± 550 kV gas‐insulated switchgear (GIS). This paper, using a finite element method for multi‐physics simulations of electric–thermal coupling, determines a geometry suitable for the industrial production of ± 550 kV GIS basin insulators.
Shaohua Cao +9 more
wiley +1 more source
A Mechanistic Digital Twin of uPAR-Driven Prostate Cancer Invasion Integrating ODE Signalling and Agent-Based Modelling. [PDF]
Dzik R +4 more
europepmc +1 more source
We bridge micro‐ and macroparasite theory with a model tracking pathogen load heterogeneity. By incorporating load‐dependent mortality and within‐host pathogen growth, we show how pathogen load aggregation alters disease prevalence, host suppression effects, and virulence evolution, providing insights for managing complex infectious disease like ...
Ruijiao Sun +3 more
wiley +1 more source

