Related references
Note: Only part of the references are listed.
Article
Computer Science, Artificial Intelligence
Zicong Xia et al.
Summary: This paper addresses the problem of Clifford-valued distributed optimization subject to linear equality and inequality constraints. It proposes a system of multiple Clifford-valued recurrent neural networks (RNNs) based on the generalized Clifford gradient for solving the optimization problems. The convergence of the neural system is rigorously proved using the Lyapunov theory. Two illustrative examples demonstrate the viability of the results in this article.
IEEE TRANSACTIONS ON NEURAL NETWORKS AND LEARNING SYSTEMS
(2023)
Article
Automation & Control Systems
Yongkun Li et al.
Summary: This paper proposes an octonion-valued neural network model and investigates the existence and stability of its almost periodic solutions using the fixed point method and the time scale calculus theory. The results show that even in continuous time real-valued systems, novel findings can be obtained.
INTERNATIONAL JOURNAL OF SYSTEMS SCIENCE
(2023)
Article
Neurosciences
Zhengwen Tu et al.
Summary: This paper focuses on the problem of H-infinity state estimation for quaternion-valued inertial neural networks (QVINNs) with nonidentical time-varying delay. A non-reduced order method is developed to investigate the addressed QVINNs, which is different from most existing references. Algebraic criteria are established to determine the asymptotic stability of the error-state system with the desired H-infinity performance by constructing a new Lyapunov functional with tuning parameters. An effective algorithm is provided for designing the estimator parameters, and a numerical example is given to illustrate the feasibility of the designed state estimator.
COGNITIVE NEURODYNAMICS
(2023)
Article
Mathematics, Applied
El Abed Assali
Summary: This paper investigates the global exponential stability of a class of Clifford-valued recurrent neural networks with time-varying delays and distributed delays. The existence of equilibrium point for Clifford-valued recurrent neural networks is established based on Brouwer's fixed point theorem. By using inequality technique and the method of the Clifford-valued variation parameter, novel assertions are given to ensure the global exponential stability of the model, which complement some previous works. The effectiveness of this approach is illustrated with a numerical example.
COMPUTATIONAL & APPLIED MATHEMATICS
(2023)
Article
Computer Science, Artificial Intelligence
Melike Solak et al.
Summary: This research article focuses on dynamical neural network models with discrete time delay terms, Lipschitz activation functions, and parameter uncertainties. A new upper bound value and stability conditions are proposed to ensure the robust stability of these models. A new general framework is established for determining the robust stability conditions using the Homeomorphism mapping theory and basic Lyapunov stability theory.
Article
Engineering, Mechanical
Bing Li et al.
Summary: This paper investigates a class of octonion-valued neutral-type stochastic recurrent neural networks with D operator. Except for the time delay, all connection weight functions, activation functions and external inputs of such networks are octonions. The existence and uniqueness of almost periodic solutions in distribution of this class of stochastic neural networks are established based on the Banach fixed point theorem, the definition of almost periodic stochastic processes in distribution and the inequality technique. The results and methods in this paper are new. Even if the network studied in this paper is a real-valued network, the results of this paper are also new. An example is provided to demonstrate the validity of the obtained results.
NONLINEAR DYNAMICS
(2023)
Article
Mathematics, Applied
Xiaoli Huang et al.
Summary: In this paper, we study octonion-valued high-order fuzzy networks with time-varying delays. By employing Banach's fixed point theorem, we prove the existence of a unique bounded and uniformly continuous solution to the system. Furthermore, we demonstrate that this solution is also a p-th Weyl almost periodic solution through the use of inequality techniques. Additionally, we investigate the global exponential stability of this almost periodic solution. Our results are novel even when the system degenerates into a real-valued system. Finally, we validate the effectiveness of our findings through a numerical example and computer simulations.
COMPUTATIONAL & APPLIED MATHEMATICS
(2023)
Article
Automation & Control Systems
Shiv Shankar Chouhan et al.
Summary: This article studies the fixed time synchronization of Octonion valued neural networks (OVNNs) with time varying delays. OVNNs do not fall into the category of Clifford valued neural networks due to their non-associativity. The article decomposes OVNNs into eight real valued systems of equations and derives several sufficient criteria for fixed time synchronization using lemmas and Lyapunov function. Additionally, a novel nonlinear controller is designed to maintain the synchronization state of the drive-response system. Finally, a numerical example is provided to validate the theoretical findings.
ENGINEERING APPLICATIONS OF ARTIFICIAL INTELLIGENCE
(2023)
Article
Automation & Control Systems
Yanxi Chen et al.
Summary: This paper focuses on analyzing the global Mittag-Leffler stability of fractional-order quaternion-valued neural networks with piecewise constant arguments and impulses. The quaternion direct method is used to address the model without any decomposition. By employing matrix inequality technique and Lyapunov direct method, sufficient conditions in the form of quaternion-valued linear matrix inequalities (LMIs) are derived to guarantee the global Mittag-Leffler stability of equilibrium point for the considered model. A numerical example is also presented to validate the obtained results.
INTERNATIONAL JOURNAL OF SYSTEMS SCIENCE
(2022)
Article
Computer Science, Artificial Intelligence
Huihui Zhang et al.
Summary: This paper investigates the synchronization issue for coupled neural networks under stochastic deception attacks, providing synchronization criteria and extending the established differential inequality to delayed stochastic impulses. By modeling stochastic discrete-time deception attacks as stochastic impulses, the paper offers theoretical results validated through numerical examples.
Article
Computer Science, Artificial Intelligence
Sunny Singh et al.
Summary: This article addresses the fixed time synchronization of a class of Quaternion valued neural networks by separating them into equivalent real valued neural networks and designing a suitable controller. Stability definitions of finite time and fixed time are proposed, and two different expressions of settling time are obtained. The theoretical results are validated through numerical simulation on a specific example.
NEURAL PROCESSING LETTERS
(2022)
Article
Multidisciplinary Sciences
Yongkun Li et al.
Summary: This paper investigates the existence and stability of Weyl almost automorphic solutions in distribution sense for a class of Clifford-valued stochastic neural networks with time-varying delays. The existence and uniqueness of the solutions are studied using the Banach fixed point theorem and inequality technique. The proposed method can also be applied to other types of neural networks.
PROCEEDINGS OF THE ROYAL SOCIETY A-MATHEMATICAL PHYSICAL AND ENGINEERING SCIENCES
(2022)
Article
Mathematics, Applied
Jin Gao et al.
Summary: This paper discusses a class of fractional-order octonion-valued neural networks with impulsive effects. By applying the appropriate Lyapunov function and inequality techniques, the global asymptotical synchronization of FOOVNNs is achieved. The feasibility of the proposed method is illustrated through two examples.
Article
Computer Science, Information Systems
Shiv Shankar Chouhan et al.
Summary: This article studies the multistability analysis of n-dimensional octonion valued neural networks (OVNNs) with time-varying delays for a general class of activation functions. The OVNNs are decomposed into eight real-valued systems, and 38n disjoint regions are constructed in On based on geometric properties of the activation functions. By using the inequality technique, several sufficient conditions are obtained to ensure the existence of 38n equilibrium points, with 28n of them being locally exponentially stable. Furthermore, the article estimates positively invariant sets and provides numerical examples to illustrate the effectiveness of the obtained results, particularly in storing and retrieving true-color images.
INFORMATION SCIENCES
(2022)
Article
Computer Science, Artificial Intelligence
Jianying Xiao et al.
Summary: This paper establishes a new case of neural networks called fractional-order octonion-valued bidirectional associative memory neural networks (FOOVBAMNNs). The higher dimensional models for FOOVBAMNNs with general activation functions and special linear threshold functions are formulated. The system of FOOVBAMNNs is divided into four fractional-order complex-valued systems using the Cayley-Dichson construction, and the Caputo fractional derivative's character and BAM's interactive feature are properly dealt with. The general criteria for the global Mittag-Leffler synchronization problem of FOOVBAMNNs are obtained, and two numerical examples are presented to show the realizability and progress of the derived results.
Article
Mathematics, Applied
G. Rajchakit et al.
Summary: This paper focuses on the global asymptotic stability problem for Clifford-valued neural network models with time-varying delays and impulsive effects. A general class of network model is considered by taking into account impulsive effects, which includes real-valued, complex-valued, and quaternion-valued neural network models as special cases. Utilizing the Lyapunov stability theory, contraction mapping principle, and some mathematical concepts, the existence and uniqueness of equilibrium points are derived, along with new sufficient conditions for global asymptotic stability.
APPLIED MATHEMATICS AND COMPUTATION
(2021)
Article
Mathematics, Interdisciplinary Applications
Yongkun Li et al.
Summary: This paper investigates the existence and global exponential stability of almost periodic solutions in distribution for a class of Clifford-valued stochastic recurrent neural networks with time-varying delays using the non-decomposition method. The study establishes the existence and uniqueness of almost periodic solutions using Banach fixed point theorem and inequality techniques, and proves the global exponential stability of the unique solution through the contradiction method.
CHAOS SOLITONS & FRACTALS
(2021)
Article
Computer Science, Information Systems
Lina Fan et al.
Summary: This paper investigates the mean square exponential stability of discrete-time stochastic neural networks with partially unstable subsystems and mixed delays. Sufficient conditions for stability are provided by constructing a novel Lyapunov-Krasovskii functional and utilizing the stationary distribution of a Markov chain. Numerical examples are presented to validate the theoretical results.
INFORMATION SCIENCES
(2021)
Article
Mathematics, Applied
Huamin Wang et al.
Summary: This article focuses on constructing an impulsive disturbed neural network model with delays in quaternion space and deriving exponential stability conditions using generalized norms. By researching the stability of the IQVDNN system, several exponential stability sufficient criteria are obtained.
APPLIED MATHEMATICS AND COMPUTATION
(2021)
Article
Mathematics
Wen Lv et al.
Summary: In this paper, Clifford-valued fuzzy neural networks with proportional delays and Clifford numbers as leakage term coefficients are investigated. By utilizing the Banach fixed point theorem and differential inequality technique, the existence, uniqueness, and global attractivity of pseudo almost periodic solutions for these networks are established using a direct method. A numerical example is provided to demonstrate the feasibility of the results, which are novel.
Article
Mathematics, Applied
Yongkun Li et al.
Summary: In this study, a class of neutral type Clifford-valued cellular neural networks with discrete delays and infinitely distributed delays is considered. The existence and uniqueness of (mu, nu)-pseudo compact almost automorphic solutions of the networks are established, and the global exponential stability of the solution is investigated using differential inequality techniques. The theoretical findings are illustrated with an example and are shown to be novel even when the networks are degenerated into real-valued, complex-valued, or quaternion-valued networks.
DISCRETE AND CONTINUOUS DYNAMICAL SYSTEMS-SERIES B
(2021)
Article
Mathematics, Applied
Yuxiao Wang et al.
APPLIED MATHEMATICS AND COMPUTATION
(2020)
Article
Mathematics, Applied
Udhayakumar Kandasamy et al.
DISCRETE AND CONTINUOUS DYNAMICAL SYSTEMS-SERIES S
(2020)
Article
Physics, Multidisciplinary
Zhengwen Tu et al.
PHYSICA A-STATISTICAL MECHANICS AND ITS APPLICATIONS
(2019)
Article
Computer Science, Artificial Intelligence
Calin-Adrian Popa
Article
Computer Science, Artificial Intelligence
Calin-Adrian Popa
Article
Automation & Control Systems
Tao Wu et al.
JOURNAL OF THE FRANKLIN INSTITUTE-ENGINEERING AND APPLIED MATHEMATICS
(2018)
Article
Engineering, Mechanical
Yang Liu et al.
NONLINEAR DYNAMICS
(2016)
Proceedings Paper
Computer Science, Artificial Intelligence
Calin-Adrian Popa
ARTIFICIAL NEURAL NETWORKS AND MACHINE LEARNING - ICANN 2016, PT I
(2016)
Article
Mathematics, Applied
Mikhail Kamenskii et al.
JOURNAL OF MATHEMATICAL ANALYSIS AND APPLICATIONS
(2015)
Article
Mathematics
Zhenxin Liu et al.
JOURNAL OF FUNCTIONAL ANALYSIS
(2014)
Article
Engineering, Electrical & Electronic
J Cao et al.
IEEE TRANSACTIONS ON CIRCUITS AND SYSTEMS I-REGULAR PAPERS
(2003)
