Results 21 to 30 of about 565,015 (288)
Data‐driven performance metrics for neural network learning
International Journal of Adaptive Control and Signal Processing, EarlyView., 2023 Summary Effectiveness of data‐driven neural learning in terms of both local mimima trapping and convergence rate is addressed. Such issues are investigated in a case study involving the training of one‐hidden‐layer feedforward neural networks with the extended Kalman filter, which reduces the search for the optimal network parameters to a state ...
Angelo Alessandri +2 more
wiley +1 more source
Sum of Exponential Model for Fitting Data
Engineering Proceedings, 2023 As an approach to feature estimation, exponential fitting has attracted research interests in mathematical modeling. Semantic networks are used for numerous applications in computers, physics, and biology.
Ting-Cheng Chang, Min-Hao Wu, Ying Lin
doaj +1 more source
Improved Convolutional Neural Network Based on Fast Exponentially Linear Unit Activation Function
IEEE Access, 2019 The activation functions play increasingly important roles in deep convolutional neural networks. The traditional activation functions have some problems such as gradient disappearance, neuron death and output offset, and so on.
Zheng Qiumei, Tan Dan, Wang Fenghua
doaj +1 more source
Fractal and Fractional, 2023 This article extends the study of q-versions of analytic functions by introducing and studying the association of starlike functions with trigonometric cosine functions, both defined in their q-versions.
Yusra Taj +5 more
doaj +1 more source
Sensors, 2019 The accuracy of thin-film characterization in terahertz spectroscopy is mainly set by the thickness uncertainty. Physical thickness measurement has limited accuracy for thin-film samples thinner than a few hundreds of micrometers and is sometimes even ...
Xuequan Chen, Emma Pickwell-MacPherson
doaj +1 more source
Advanced Engineering Materials, EarlyView., 2023 The study presents the mechanical and in situ sensing performance of digital light processing‐enabled 2D lattice nanocomposites under monotonic tensile and repeated cyclic loading, and provides guidelines for the design of architectures suitable for strain sensors and smart lightweight structures.
Omar Waqas Saadi +3 more
wiley +1 more source
Creep Characterization of Inconel 718 Lattice Metamaterials Manufactured by Laser Powder Bed Fusion
Advanced Engineering Materials, EarlyView., 2023 Herein, the creep characteristics of additively manufactured Inconel 718 metamaterials are investigated. The creep behavior of metamaterials and the effects of microstructural defects are assessed, and the microstructure defects are accurately captured using Kachanov's creep damage model.
Akash Singh Bhuwal +5 more
wiley +1 more source
Increasing property and logarithmic convexity of functions involving Dirichlet lambda function
Demonstratio Mathematica, 2023 In this article, with the help of an integral representation of the Dirichlet lambda function, by means of a monotonicity rule for the ratio of two integrals with a parameter, and by virtue of complete monotonicity and another property of an elementary ...
Qi Feng, Lim Dongkyu
doaj +1 more source
Flexural Behavior of Bidirectionally Graded Lattice
Advanced Engineering Materials, EarlyView., 2023 An experimental study of the bending behavior of bidirectional body‐centered cubic lattice beams is conducted in comparison to uniform and unidirectional counterparts of electron beam melted SS 316 L. Experimental results are used to develop and validate a finite element model which is subsequently used to conduct parametric studies to assess the ...
Chamini Rodrigo +4 more
wiley +1 more source
Exponential-Based Testability Index Allocation and Feasibility Analysis Method
IEEE Access, 2021 Existing mainstream testability index allocation (TIA) methods have the problem that the allocation value cannot reflect the index changes with the failure rate. One of the main reasons is that most of the existing methods use linear allocation functions,
Yixin Hu, Yigang Sun, Jiao Xue
doaj +1 more source