Results 131 to 140 of about 1,311 (253)

Double‐Integration‐Enhanced Stochastic Gradient Descent Based on Neural Dynamics for Improving Generalisation

open access: yesCAAI Transactions on Intelligence Technology, EarlyView.
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

Quadratic Motion Polynomials with Irregular Factorizations. [PDF]

open access: yesAdv Appl Clifford Algebr
Thimm DA   +3 more
europepmc   +1 more source

ANPGT: Towards Adaptive Node Property Extraction and Integration

open access: yesCAAI Transactions on Intelligence Technology, EarlyView.
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

Fault‐Tolerant Fuzzy Boundary Control for Nonlinear Distributed Parameter Systems Under Limited Measurements and Markovian Failures

open access: yesCAAI Transactions on Intelligence Technology, EarlyView.
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

Distributed k‐WTA Network for Multi‐Manipulator Competition With Experimental Verifications

open access: yesCAAI Transactions on Intelligence Technology, EarlyView.
ABSTRACT In this article, a new distributed k $k$‐winner‐take‐all (Dk $k$‐WTA) network is designed and used to construct a dynamic allocation scheme for competitive coordination tasks of multiple manipulators as embodied agents. The scheme is constructed based on the following two aspects. On one hand, with reference to a perspective that the Laplacian
Shengkai Sun, Yutong Li, Jianfeng Lv
wiley   +1 more source

Arc Resistance Enhancement of Converter Transformer Tank Through Structural Improvements: Simulation and Experimental Validation

open access: yesHigh Voltage, EarlyView.
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

Home - About - Disclaimer - Privacy