本文選題：時(shí)標(biāo)　切入點(diǎn)：神經(jīng)網(wǎng)絡(luò)　出處：《集美大學(xué)》2017年碩士論文　論文類型：學(xué)位論文

【摘要】：近年來(lái),隨著時(shí)標(biāo)理論的提出,時(shí)標(biāo)動(dòng)力學(xué)方程及其應(yīng)用引起了各國(guó)學(xué)者的廣泛關(guān)注.時(shí)標(biāo)動(dòng)力學(xué)方程在研究系統(tǒng)時(shí)更具一般性,不僅能描述連續(xù)變化過(guò)程和離散變化過(guò)程,而且可以刻畫連續(xù)和離散混合的過(guò)程.因此,時(shí)標(biāo)理論在金融,生物系統(tǒng),復(fù)雜網(wǎng)絡(luò)和工程應(yīng)用等方面具有廣泛的應(yīng)用前景.然而,時(shí)標(biāo)動(dòng)力學(xué)理論在神經(jīng)網(wǎng)絡(luò)的應(yīng)用研究相對(duì)較少,尚有很多動(dòng)力學(xué)行為有待進(jìn)一步研究,特別是神經(jīng)網(wǎng)絡(luò)的穩(wěn)定性,多重周期性以及同步控制問(wèn)題.基于前人的基礎(chǔ),我們引入時(shí)標(biāo)上微積分理論研究了時(shí)標(biāo)上神經(jīng)網(wǎng)絡(luò)的穩(wěn)定性、周期解和同步性.本文分析了時(shí)標(biāo)上幾類網(wǎng)絡(luò)模型的動(dòng)力學(xué)性質(zhì).主要內(nèi)容包括:第一部分研究了時(shí)標(biāo)上含N段激活函數(shù)的一類2維神經(jīng)網(wǎng)絡(luò)的指數(shù)型周期解,獲得系統(tǒng)存在N2個(gè)周期解并且解是指數(shù)型穩(wěn)定的.第二部分研究了時(shí)標(biāo)上一類簡(jiǎn)化背景神經(jīng)網(wǎng)絡(luò)的完全收斂性,證明了網(wǎng)絡(luò)的完全收斂性,有界性和具有全局吸引集.第三部分解決了在q-容許時(shí)標(biāo)上具有比例時(shí)滯的一類神經(jīng)網(wǎng)絡(luò)的同步控制問(wèn)題,解決了離散條件下帶比例時(shí)滯的網(wǎng)絡(luò)的同步控制問(wèn)題.
[Abstract]:In recent years, with the development of the theory of time scale, the dynamic equation of time scale and its application have attracted the attention of scholars all over the world. The dynamic equation of time scale is more general in the study of the system, and it can not only describe the continuous change process and discrete change process. Therefore, time scale theory has a wide range of applications in finance, biological systems, complex networks and engineering applications. The application of time-scale dynamics theory in neural networks is relatively few, and there are still many dynamic behaviors to be further studied, especially the stability, multiple periodicity and synchronization control of neural networks. In this paper, we introduce the calculus theory of time scale to study the stability of time scale neural network. In this paper, the dynamical properties of several network models on time scales are analyzed. The main contents are as follows: in the first part, the exponential periodic solutions of a class of two-dimensional neural networks with N segment activation function are studied. It is obtained that there are N _ 2 periodic solutions and the solutions are exponential stable. In the second part, the complete convergence of a class of simplified background neural networks on time scales is studied, and the complete convergence of the network is proved. In the third part, the synchronization control problem of a class of neural networks with proportional delay on q-admissible time scale is solved, and the synchronization control problem of a network with proportional delay under discrete conditions is solved.
【學(xué)位授予單位】：集美大學(xué)
【學(xué)位級(jí)別】：碩士
【學(xué)位授予年份】：2017
【分類號(hào)】：O175;O231

【參考文獻(xiàn)】

相關(guān)博士學(xué)位論文 前1條

1 徐軍;遞歸神經(jīng)網(wǎng)絡(luò)穩(wěn)定性分析[D];浙江大學(xué);2007年

相關(guān)碩士學(xué)位論文 前1條

1 谷群花;時(shí)標(biāo)上幾類神經(jīng)網(wǎng)絡(luò)的定性研究[D];湘潭大學(xué);2009年

，

本文編號(hào)：1564969