4.6 Article

Multiple exponential stability and instability for state-dependent switched neural networks with time-varying delays and piecewise-linear radial basis activation functions

Related references

Note: Only part of the references are listed.
Article Automation & Control Systems

Multimode function multistability for Cohen-Grossberg neural networks with mixed time delays

Liguang Wan et al.

Summary: This paper investigates the multimode function multistability for Cohen-Grossberg neural networks (CGNNs) with mixed time delays, and presents its mathematical expression and criteria. Multiple types of multistability can be achieved by selecting different types of function P(t). The generality of the obtained criteria is substantiated through numerical examples.

ISA TRANSACTIONS (2022)

Article Computer Science, Theory & Methods

Almost periodic synchronization of quaternion-valued fuzzy cellular neural networks with leakage delays

Pan Wang et al.

Summary: This paper studies the synchronization issue of quaternion-valued fuzzy cellular neural networks (QVFCNNs) with leakage delays by decomposing them into an analogous real-valued system and investigating the existence of almost periodic solutions based on the Banach fixed point theorem. A novel state-feedback controller is designed to ensure the synchronization of global exponential almost periodicity. The effectiveness of the results is illustrated through two examples.

FUZZY SETS AND SYSTEMS (2022)

Article Engineering, Electrical & Electronic

A training strategy for improving the robustness of memristor-based binarized convolutional neural networks

Lixing Huang et al.

Summary: Memristor-based convolutional neural networks (CNNs) have been extensively studied in the field of edge computing due to their high integration density and powerful processing capability. However, the low yield of memristor array and the variation in memristance pose limitations for the widespread application of memristor-based CNNs. To address this issue, a training strategy is proposed to enhance the robustness of memristor-based binarized neural networks for embedded applications.

SEMICONDUCTOR SCIENCE AND TECHNOLOGY (2022)

Article Automation & Control Systems

Energy analysis of a class of state-dependent switched systems with all unstable subsystems

Danhong Chen et al.

Summary: This paper investigates the stability and periodicity of a class of state-dependent switched systems with all unstable subsystems by means of energy analysis. A method for designing a state-dependent switching law is proposed and validated through numerical simulation.

JOURNAL OF THE FRANKLIN INSTITUTE-ENGINEERING AND APPLIED MATHEMATICS (2021)

Article Automation & Control Systems

Multiple ψ-Type Stability of Cohen-Grossberg Neural Networks With Unbounded Time-Varying Delays

Fanghai Zhang et al.

Summary: This paper investigates the existence condition of multiple equilibrium points in Cohen-Grossberg neural networks with unbounded time-varying delays using the algebraic inequality method. It also studies phi-type stability and the adjustment of relative convergence rate by selecting phi-type functions for CGNNs with unbounded time-varying delays. Furthermore, the introduction of topological degree ensures that the algebraic sum of equilibria remains unchanged for any smooth function in the specified metric space.

IEEE TRANSACTIONS ON SYSTEMS MAN CYBERNETICS-SYSTEMS (2021)

Article Computer Science, Hardware & Architecture

Empirical study on tangent loss function for classification with deep neural networks

Xu Zhang et al.

Summary: Researchers proposed a new loss function, namely tangent loss (TG), to improve the stability of classification models and achieve comparable performance. Systematic empirical studies on TG loss compared with CE loss demonstrated its effectiveness in enhancing classification models' stability.

COMPUTERS & ELECTRICAL ENGINEERING (2021)

Article Computer Science, Hardware & Architecture

Flux Controlled Floating Memristor Employing VDTA: Incremental or Decremental Operation

John Vista et al.

Summary: This research introduces a floating memristor model using VDTA and passive components, demonstrating both incremental and decremental modes of operation. The performance of the memristor is analyzed through simulation and experiment, with application perspectives including Pavlovian associative learning experiments.

IEEE TRANSACTIONS ON COMPUTER-AIDED DESIGN OF INTEGRATED CIRCUITS AND SYSTEMS (2021)

Article Computer Science, Artificial Intelligence

Multistability for Almost-Periodic Solutions of Takagi-Sugeno Fuzzy Neural Networks With Nonmonotonic Discontinuous Activation Functions and Time-Varying Delays

Peng Wan et al.

Summary: This article investigates the multistability of almost-periodic solutions of Takagi-Sugeno fuzzy neural networks with nonmonotonic discontinuous activation functions and time-varying delays. By analyzing the geometric properties of nonmonotonic activation functions, it is demonstrated that the addressed networks have a locally exponentially stable almost-periodic solution under certain conditions. The study also estimates the attraction basins, showing that they can be larger than the original hyperrectangular regions.

IEEE TRANSACTIONS ON FUZZY SYSTEMS (2021)

Article Computer Science, Artificial Intelligence

Multi-valued neural networks I: a multi-valued associative memory

Dmitry Maximov et al.

Summary: This paper introduces a new concept of multi-valued associative memory, generalizing a similar concept in fuzzy neural networks. The network does not require numerical representation of weights and data, can store given pairs of network variable patterns, and builds network output using lattice operations.

NEURAL COMPUTING & APPLICATIONS (2021)

Article Computer Science, Artificial Intelligence

Multiple O(t-q) stability and instability of time-varying delayed fractional-order Cohen-Grossberg neural networks with Gaussian activation functions

Liguang Wan et al.

Summary: This paper introduces new theoretical results on the multiple O(t(-q)) stability and instability of a class of time-varying delayed fractional-order Cohen-Grossberg neural networks (FoCGNNs) with Gaussian activation functions. The state space is partitioned into subspaces based on the model and Gaussian functions, with unique equilibrium points guaranteed in each subspace. The sufficient conditions for stability and instability of equilibrium points are discussed and demonstrated with examples.

NEUROCOMPUTING (2021)

Article Computer Science, Artificial Intelligence

Finite-/Fixed-Time Synchronization of Delayed Coupled Discontinuous Neural Networks With Unified Control Schemes

Jian Xiao et al.

Summary: This article addresses the finite-/fixed-time synchronization of delayed coupled discontinuous neural networks using novel controllers, achieving synchronization within a specified time frame. Criteria for selecting controller parameters and estimating setting time are provided based on finite-time/fixed-time theorem and Lyapunov function theory. Numerical examples demonstrate the effectiveness of the proposed control protocols.

IEEE TRANSACTIONS ON NEURAL NETWORKS AND LEARNING SYSTEMS (2021)

Article Automation & Control Systems

Robust Stability of Recurrent Neural Networks With Time-Varying Delays and Input Perturbation

Fanghai Zhang et al.

Summary: This study investigates the robust stability and boundedness of recurrent neural networks with time-varying delays and input perturbation, revealing a relationship between neural network stability and input perturbation. The proposed conditions improve and extend existing stability results in literature.

IEEE TRANSACTIONS ON CYBERNETICS (2021)

Article Automation & Control Systems

Multiple Lagrange Stability Under Perturbation for Recurrent Neural Networks With Time-Varying Delays

Fanghai Zhang et al.

IEEE TRANSACTIONS ON SYSTEMS MAN CYBERNETICS-SYSTEMS (2020)

Article Automation & Control Systems

Multistability of Recurrent Neural Networks With Piecewise-Linear Radial Basis Functions and State-Dependent Switching Parameters

Zhenyuan Guo et al.

IEEE TRANSACTIONS ON SYSTEMS MAN CYBERNETICS-SYSTEMS (2020)

Article Computer Science, Artificial Intelligence

Multistability of switched neural networks with sigmoidal activation functions under state-dependent switching

Zhenyuan Guo et al.

NEURAL NETWORKS (2020)

Article Computer Science, Artificial Intelligence

Hopfield neural networks using Klein four-group

Masaki Kobayashi

NEUROCOMPUTING (2020)

Article Automation & Control Systems

Stability of delayed switched systems with state-dependent switching

Chao Liu et al.

IEEE-CAA JOURNAL OF AUTOMATICA SINICA (2020)

Article Computer Science, Artificial Intelligence

Synchronization of coupled neural networks under mixed impulsive effects: A novel delay inequality approach

Yaqi Wang et al.

NEURAL NETWORKS (2020)

Article Mathematics, Interdisciplinary Applications

Relaxation and mixed mode oscillations in a shape memory alloy oscillator driven by parametric and external excitations

Yue Yu et al.

CHAOS SOLITONS & FRACTALS (2020)

Article Computer Science, Artificial Intelligence

Multiple ψ-Type Stability of Cohen-Grossberg Neural Networks With Both Time-Varying Discrete Delays and Distributed Delays

Fanghai Zhang et al.

IEEE TRANSACTIONS ON NEURAL NETWORKS AND LEARNING SYSTEMS (2019)

Article Computer Science, Artificial Intelligence

Multistability of Switched Neural Networks With Piecewise Linear Activation Functions Under State-Dependent Switching

Zhenyuan Guo et al.

IEEE TRANSACTIONS ON NEURAL NETWORKS AND LEARNING SYSTEMS (2019)

Article Computer Science, Artificial Intelligence

Multistability in Mittag-Leffler sense of fractional-order neural networks with piecewise constant arguments

Liguang Wan et al.

NEUROCOMPUTING (2018)

Article Computer Science, Artificial Intelligence

Dynamics of complex-valued neural networks with variable coefficients and proportional delays

Qiankun Song et al.

NEUROCOMPUTING (2018)

Article Engineering, Multidisciplinary

Synchronization criteria for multiple memristor-based neural networks with time delay and inertial term

Ning Li et al.

SCIENCE CHINA-TECHNOLOGICAL SCIENCES (2018)

Article Computer Science, Artificial Intelligence

Complete stability of delayed recurrent neural networks with Gaussian activation functions

Peng Liu et al.

NEURAL NETWORKS (2017)

Article Engineering, Mechanical

Routes to bursting in active control system with multiple time delays

Yue Yu et al.

NONLINEAR DYNAMICS (2017)

Article Computer Science, Artificial Intelligence

Exponential Synchronization of Memristive Neural Networks With Delays: Interval Matrix Method

Xinsong Yang et al.

IEEE TRANSACTIONS ON NEURAL NETWORKS AND LEARNING SYSTEMS (2017)

Article Computer Science, Artificial Intelligence

A unified associative memory model based on external inputs of continuous recurrent neural networks

Caigen Zhou et al.

NEUROCOMPUTING (2016)

Article Automation & Control Systems

Multistability of Recurrent Neural Networks With Nonmonotonic Activation Functions and Mixed Time Delays

Peng Liu et al.

IEEE TRANSACTIONS ON SYSTEMS MAN CYBERNETICS-SYSTEMS (2016)

Article Computer Science, Artificial Intelligence

Passivity of Switched Recurrent Neural Networks With Time-Varying Delays

Jie Lian et al.

IEEE TRANSACTIONS ON NEURAL NETWORKS AND LEARNING SYSTEMS (2015)

Article Computer Science, Artificial Intelligence

Global Exponential Synchronization of Multiple Memristive Neural Networks With Time Delay via Nonlinear Coupling

Zhenyuan Guo et al.

IEEE TRANSACTIONS ON NEURAL NETWORKS AND LEARNING SYSTEMS (2015)

Article Computer Science, Artificial Intelligence

New global exponential stability results for a memristive neural system with time-varying delays

Ailong Wu et al.

NEUROCOMPUTING (2014)

Article Computer Science, Artificial Intelligence

Multistability of Two Kinds of Recurrent Neural Networks With Activation Functions Symmetrical About the Origin on the Phase Plane

Zhigang Zeng et al.

IEEE TRANSACTIONS ON NEURAL NETWORKS AND LEARNING SYSTEMS (2013)

Article Computer Science, Artificial Intelligence

Dynamic behaviors of memristor-based recurrent neural networks with time-varying delays

Ailong Wu et al.

NEURAL NETWORKS (2012)

Article Computer Science, Artificial Intelligence

Multistability of Neural Networks With Mexican-Hat-Type Activation Functions

Lili Wang et al.

IEEE TRANSACTIONS ON NEURAL NETWORKS AND LEARNING SYSTEMS (2012)

Article Computer Science, Artificial Intelligence

Multistability of Neural Networks with Time-Varying Delays and Concave-Convex Characteristics

Zhigang Zeng et al.

IEEE TRANSACTIONS ON NEURAL NETWORKS AND LEARNING SYSTEMS (2012)

Article Computer Science, Artificial Intelligence

Exponential synchronization of memristor-based recurrent neural networks with time delays

Ailong Wu et al.

NEUROCOMPUTING (2011)

Article Computer Science, Artificial Intelligence

Multistability of Recurrent Neural Networks with Time-varying Delays and the Piecewise Linear Activation Function

Zhigang Zeng et al.

IEEE TRANSACTIONS ON NEURAL NETWORKS (2010)

Article Mathematics, Applied

Quadratic Lyapunov functions for systems with state-dependent switching

Wynita M. Griggs et al.

LINEAR ALGEBRA AND ITS APPLICATIONS (2010)