Výsledky vyhľadávania - Numerical algorithms for specific classes of architectures

A Universal Approximation Result for Difference of Log-Sum-Exp Neural Networks Autor Calafiore, Giuseppe C., Gaubert, Stephane, Possieri, Corrado

“… By using a logarithmic transform, this class of network maps to a family of subtraction-free ratios of generalized posynomials (GPOS…”
Získať plný text

Random-Effect Models for Degradation Analysis Based on Nonlinear Tweedie Exponential-Dispersion Processes Autor Chen, Zhen, Xia, Tangbin, Li, Yaping, Pan, Ershun

“… If such a specific degradation model is wrongly assumed, then poor analysis results of reliability assessment would be obtained…”
Získať plný text

Architectures and accuracy of artificial neural network for disease classification from omics data Autor Yu, Hui, Samuels, David C., Zhao, Ying-yong, Guo, Yan

“…Background Deep learning has made tremendous successes in numerous artificial intelligence applications and is unsurprisingly penetrating into various…”
Získať plný text

Alternative Distributed Algorithms for Network Utility Maximization: Framework and Applications Autor Palomar, D.P., Mung Chiang

“… structures as a way to obtain different distributed algorithms, each with a different tradeoff among convergence speed…”
Získať plný text

A Parallel Adaptive Coupling Algorithm for Systems of Differential Equations Autor Garbey, M., Tromeur-Dervout, D.

“…In this paper we address the challenge of metacomputing with two distant parallel computers linked by a slow network and running the numerical approximation of two sets of coupled PDEs…”
Získať plný text

Universal Approximation Abilities of a Modular Differentiable Neural Network Autor Wang, Jian, Wu, Shujun, Zhang, Huaqing, Yuan, Bin, Dai, Caili, Pal, Nikhil R.

“… Moreover, an adequate level of interpretability of the networks is missing as well. In this work, we propose a class of new network architecture, built with reusable neural modules (functional blocks…”
Získať plný text

A Framework for Dynamic Network Architecture and Topology Optimization Autor Shams Shafigh, Alireza, Lorenzo, Beatriz, Glisic, Savo, Perez-Romero, Jordi, DaSilva, Luiz A., MacKenzie, Allen B., Juha Roning

“…A new paradigm in wireless network access is presented and analyzed. In this concept, certain classes of wireless terminals can be turned temporarily into an access point (AP…”
Získať plný text

Neural Network Architecture for Cognitive Navigation in Dynamic Environments Autor Villacorta-Atienza, Jose Antonio, Makarov, Valeri A.

“… tasks. CIR is a specific cognitive map that compacts time-evolving situations into static structures containing information necessary for navigation…”
Získať plný text

An Online Approach to Estimate Parameters of Phase-Type Distributions Autor Buchholz, Peter, Dohndorf, Iryna, Kriege, Jan

“…), a widely used class of distributions in performance and dependability modeling. EM algorithms are typical offline algorithms because they improve the likelihood function by iteratively running through a fixed sample…”
Získať plný text

Scalable Proximal Jacobian Iteration Method With Global Convergence Analysis for Nonconvex Unconstrained Composite Optimizations Autor Zhang, Hengmin, Qian, Jianjun, Gao, Junbin, Yang, Jian, Xu, Chunyan

“…>-norm and rank function minimization problems. However, due to the absence of convexity in these nonconvex problems, developing efficient algorithms with convergence guarantee becomes very challenging…”
Získať plný text

Novel Discretized Zeroing Neural Network Models for Time-Varying Optimization Aided With Predictor-Corrector Methods Autor Kong, Ying, Chen, Xi, Jiang, Yunliang, Sun, Danfeng, Zhang, Jun

“…In this article, we derive the predictor-corrector (PC) methods with three-order convergent precision, together with a class of specific general linear three-step (GLTS) rules provided…”
Získať plný text

PERMANENT DECOMPOSITION ALGORITHM FOR THE COMBINATORIAL OBJECTS GENERATION Autor Turbal, Y. V., Babych, S. V., Kunanets, N. E.

“…Context. The problem of generating vectors consisting of different representatives of a given set of sets is considered. Such problems arise, in particular, in…”
Získať plný text

Convergence and Rate Analysis of Neural Networks for Sparse Approximation Autor Balavoine, A., Romberg, J., Rozell, C. J.

“… However, the LCA lacks analysis of its convergence properties, and previous results on neural networks for nonsmooth optimization do not apply to the specifics of the LCA architecture…”
Získať plný text

Gaussian process latent class choice models Autor Sfeir, Georges, Rodrigues, Filipe, Abou-Zeid, Maya

“…•Integration of machine learning and discrete choice models.•New choice model referred to as Gaussian process latent class choice model…”
Získať plný text

Game Dynamics and Cost of Learning in Heterogeneous 4G Networks Autor Khan, M. A., Tembine, H., Vasilakos, A. V.

“… of the users that we have experimented on OPNET simulations. Considering a dynamic and uncertain environment where the users and operators have only a numerical value…”
Získať plný text

Decomposition Techniques for Multilayer Perceptron Training Autor Grippo, Luigi, Manno, Andrea, Sciandrone, Marco

“… We define a wide class of batch learning algorithms for MLP, based on the use of block decomposition techniques in the minimization of the error function…”
Získať plný text

POD acceleration of fully implicit solver for unsteady nonlinear flows and its application on grid architecture Autor Tromeur-Dervout, D., Vassilevski, Y.

“… This approach is appealing to GRID computing: spare processors may help to improve the numerical efficiency and to manage the computing in a reliable way…”
Získať plný text

Regenerative exact simulation for multiserver job model Autor Golovin, Alexander, Rumyantsev, Alexander, Chakravarthy, Srinivas

“… However, to apply perfect sampling techniques to specific models, additional techniques are required…”
Získať plný text

Approximation of One-Dimensional Darcy–Brinkman–Forchheimer Model by Physics Informed Deep Learning Feedforward Artificial Neural Network and Finite Element Methods: A Comparative Study Autor Martinez, Mara, Rao, B. Veena S. N., Mallikarjunaiah, S. M.

“… (or simulated neural networks )—a class of machine learning algorithms—has gained a lot of attention due to its applicability in various science and engineering fields…”
Získať plný text

Certifying the Floating-Point Implementation of an Elementary Function Using Gappa Autor de Dinechin, Florent, Lauter, C, Melquiond, G

“…High confidence in floating-point programs requires proving numerical properties of final and intermediate values…”
Získať plný text