• Computers and Concrete
• /
• v.30 no.4
• /
• pp.237-242
• /
• 2022

This paper is concerned with exponential stability in mean square for stochastic static neutral neural networks with varying delays. By using Lyapunov functional method and with the help of stochastic analysis technique, the sufficient conditions to guarantee the exponential stability in mean square for the neural networks are obtained and some results of related literature are extended.

• Journal of Institute of Control, Robotics and Systems
• /
• v.6 no.3
• /
• pp.263-272
• /
• 2000

In this paper we give some geometric condition for a stochastic nonlinear system and we propose a control method for a stochastic nonlinear system using neural networks. Since a competitive learning neural networks has been developed based on the stochastcic approximation method it is regarded as a stochastic recursive filter algorithm. In addition we provide a filtering and control condition for a stochastic nonlinear system called the perfect filtering condition in a viewpoint of stochastic geometry. The stochastic nonlinear system satisfying the perfect filtering condition is decoupled with a deterministic part and purely semi martingale part. Hence the above system can be controlled by conventional control laws and various intelligent control laws. Computer simulation shows that the stochastic nonlinear system satisfying the perfect filtering condition is controllable and the proposed neural controller is more efficient than the conventional LQG controller and the canonical LQ-Neural controller.

• Proceedings of the Korean Institute of Intelligent Systems Conference
• /
• 1998.10a
• /
• pp.346-352
• /
• 1998

In this paper, we give some geometric condition for a stochastic nonlinear system and we propose a control method for a stochastic nonlinear system using neural networks. Since a competitive learning neural networks has been developed based on the stochastic approximation method, it is regarded as a stochastic recursive filter algorithm. In addition, we provide a filtering and control condition for a stochastic nonlinear system, called perfect filtering condition, in a viewpoint of stochastic geometry. The stochastic nonlinear system satisfying the perfect filtering condition is decoupled with a deterministic part and purely semi martingale part. Hence, the above system can be controlled by conventional control laws and various intelligent control laws. Computer simulation shows that the stochastic nonlinear system satisfying the perfect filtering condition is controllable. and the proposed neural controller is more efficient than the conventional LQG controller and the canoni al LQ-Neural controller.

• Advances in Computational Design
• /
• v.9 no.2
• /
• pp.97-113
• /
• 2024

In this paper, we proposed a new class of stochastic neutral neural networks with uncertain and deterministic coefficients. Made the Sigmund activation and Lipschitz activation functions less conditional. The Lyapnov-Krasovskii functional is constructed. The linear matrix inequality (LMI) is constructed using Schur's lemma, and new criteria for the global asymptotic stability and global asymptotic robust stability of neural networks are obtained. Furthermore, we have verified that the method is effective and feasible through numerical examples.

• Bulletin of the Korean Mathematical Society
• /
• v.48 no.4
• /
• pp.725-736
• /
• 2011

By using the Lyapunov functional method, stochastic analysis, and LMI (linear matrix inequality) approach, the mean square exponential stability of an equilibrium solution of uncertain stochastic Hopfield neural networks with delayed is presented. The proposed result generalizes and improves previous work. An illustrative example is also given to demonstrate the effectiveness of the proposed result.

• Structural Engineering and Mechanics
• /
• v.32 no.1
• /
• pp.71-94
• /
• 2009

In this paper a procedure for Monte Carlo simulation of univariate stationary stochastic processes with the aid of neural networks is presented. Neural networks operate model-free and, thus, circumvent the need of specifying a priori statistical properties of the process, as needed traditionally. This is particularly advantageous when only limited data are available. A neural network can capture the "pattern" of a short observed time series. Afterwards, it can directly generate stochastic process realizations which capture the properties of the underlying data. In the present study a simple feed-forward network with focused time-memory is utilized. The proposed procedure is demonstrated by examples of Monte Carlo simulation, by synthesis of future values of an initially short single process record.

• Journal of the Korean Mathematical Society
• /
• v.50 no.6
• /
• pp.1165-1181
• /
• 2013

In this paper, we consider a class of periodic It$\hat{o}$ stochastic delay differential equations by using the properties of periodic Markov processes, and some sufficient conditions for the existence of periodic solution of the delay equations are given. These existence theorems improve the results obtained by It$\hat{o}$ et al. [6], Bainov et al. [1] and Xu et al. [15]. As applications, we study the existence of periodic solution of periodic stochastic logistic equation and periodic stochastic neural networks with infinite delays, respectively. The theorem for the existence of periodic solution of periodic stochastic logistic equation improve the result obtained by Jiang et al. [7].

• Proceedings of the Korea Water Resources Association Conference
• /
• 2010.05a
• /
• pp.1346-1349
• /
• 2010

The goal of this research is to apply the neural networks models for the disaggregation of the pan evaporation (PE) data, Republic of Korea. The neural networks models consist of generalized regression neural networks model (GRNNM) and multilayer perceptron neural networks model (MLP-NNM), respectively. The disaggregation means that the yearly PE data divides into the monthly PE data. And, for the performances of the neural networks models, they are composed of training and test performances, respectively. The training and test performances consist of the historic, the generated, and the mixed data, respectively. From this research, we evaluate the impact of GRNNM and MLP-NNM for the disaggregation of the nonlinear time series data. We should, furthermore, construct the credible data of the monthly PE from the disaggregation of the yearly PE data, and can suggest the methodology for the irrigation and drainage networks system.

• Structural Engineering and Mechanics
• /
• v.78 no.5
• /
• pp.529-543
• /
• 2021

Inevitable source-uncertainties in geometry configuration, boundary condition, and material properties may deviate the structural dynamics from its expected responses. This paper aims to examine the influence of these uncertainties on the vibration of functionally graded beams. Finite element procedures are presented for Timoshenko beams and utilized to generate reliable datasets. A prerequisite to the uncertainty quantification of the beam vibration using Monte Carlo simulation is generating large datasets, that require executing the numerical procedure many times leading to high computational cost. Utilizing artificial neural networks to model beam vibration can be a good approach. Initially, the optimal network for each beam configuration can be determined based on numerical performance and probabilistic criteria. Instead of executing thousands of times of the finite element procedure in stochastic analysis, these optimal networks serve as good alternatives to which the convergence of the Monte Carlo simulation, and the sensitivity and probabilistic vibration characteristics of each beam exposed to randomness are investigated. The simple procedure presented here is efficient to quantify the uncertainty of different stochastic behaviors of composite structures.

• Korea-Australia Rheology Journal
• /
• v.14 no.4
• /
• pp.161-174
• /
• 2002

A new technique for numerical calculation of viscoelastic flow based on the combination of Neural Net-works (NN) and Brownian Dynamics simulation or Stochastic Simulation Technique (SST) is presented in this paper. This method uses a "universal approximator" based on neural network methodology in combination with the kinetic theory of polymeric liquid in which the stress is computed from the molecular configuration rather than from closed form constitutive equations. Thus the new method obviates not only the need for a rheological constitutive equation to describe the fluid (as in the original Calculation Of Non-Newtonian Flows: Finite Elements St Stochastic Simulation Techniques (CONNFFESSIT) idea) but also any kind of finite element-type discretisation of the domain and its boundary for numerical solution of the governing PDE's. As an illustration of the method, the time development of the planar Couette flow is studied for two molecular kinetic models with finite extensibility, namely the Finitely Extensible Nonlinear Elastic (FENE) and FENE-Peterlin (FENE-P) models.P) models.