项目名称: 分数阶随机神经网络的同步与状态估计研究
项目编号: No.61203096
项目类型: 青年科学基金项目
立项/批准年度: 2013
项目学科: 自动化学科
项目作者: 包海波
作者单位: 西南大学
项目金额: 23万元
中文摘要: 分数阶随机神经网络的同步及状态估计研究是神经网络研究领域的一个前沿性课题。研究网络的同步,发现其内在机理有助于人们更好地解释各种生活现象进而指导实践;神经元的状态估计是神经网络诸多应用的前提基础。本项目借助非线性系统理论、分数阶微积分理论及复杂网络理论等方法,结合数学模型分析和计算机模拟等手段从事以下研究:(1)建立分数阶随机神经网络模型,研究其稳定性,给出相同条件下系统稳定的阶次范围;(2)基于所建模型,针对有噪声干扰、系统存在丢包现象的情况,研究其同步的发生机理和条件,揭示分数阶次、噪声、耦合强度等对同步能力的影响,给出一些广泛适用的同步准则;(3)研究分数阶不连续随机神经网络的状态估计,确定分数阶次对状态估计器存在条件及形式的影响。本项目的实施不仅对推动分数阶系统理论的发展与完善有重要的意义,而且为分数阶随机神经网络的建模提供了新的思路。
中文关键词: 分数阶;神经网络;同步;基于忆阻器的;
英文摘要: Synchronization and state estimation of fractional stochastic neural networks are advanced topics in the fields of neural networks. Research on synchronization is not only of important theoretical value but also of practice significance. State estimation of the neurons is the foundation of neural networks applications. By means of the theory of nonlinear system, fractional calculus, theory of complex networks, combing with mathematical models analysis and computer simulations, this project aims to investigate the following items: (1)We will build fractional stochastic neural models and study their stability. The range of fractional order when the systems are stable will be given. (2)Synchronization problem will be mainly researched for fractional neural networks with noises and package loss. Several criteria of achieving synchronization will be established, and how the fractional order, noises, coupling strength influence the synchronization will be showed. (3)The state estimation of fractional discontinuous stochastic neural networks will be investigated. We will give how the fractional order effects the existence and the form of the estiamtor. Putting this project into pratice will push the development of fractional order system theory and provide a new mind for constructing fractional stochastic neural
英文关键词: fractional-order;neural networks;synchronization;memeristor-based;