Results 161 to 170 of about 2,320 (298)
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
A Quantised Push‐Sum Distributed Adaptive Momentum Algorithm for Optimisation Over Directed Networks
ABSTRACT In this paper, we investigate a distributed constrained optimisation problem over directed networks. The agents in the networks conduct local computations and communications, endeavouring to collaboratively minimise the aggregation of all locally known convex cost functions subject to a global constraint set.
Qingguo Lü +6 more
wiley +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
ANPGT: Towards Adaptive Node Property Extraction and Integration
ABSTRACT Graph transformers (GTs) with elaborate positional/structural encodings (PEs/SEs) have excelled in graph representation learning, especially in graph‐level tasks. However, their potential in large‐scale node classification remains untapped for several reasons: (i) Current PEs/SEs are insufficient in modelling large‐scale real‐world graphs ...
Qin Chen +4 more
wiley +1 more source
Threshold cryptography with Chinese remainder theorem
Cataloged from PDF version of article.Includes bibliographical references leaves 84-91.Information security has become much more important since electronic communication is started to be used in our daily life.
Kaya, Kamer
core
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 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
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
Quantum Codes from Galois Hulls of Constacyclic Codes over a Finite Non-Chain Ring. [PDF]
Zhang E, Kong B, Zheng X.
europepmc +1 more source
ABSTRACT Currently, limited research exists on the structural response and protection methods of the converter transformer tank for ± 800 kV ultra‐high voltage direct current transmission project to high energy arc faults. This research investigates the dynamic response and the vulnerable areas of the ultra‐high voltage converter transformer under the ...
Ke Wang +5 more
wiley +1 more source

