線性約束條件下任意凸函數(shù)的神經(jīng)網(wǎng)絡(luò)優(yōu)化模型
A NEURAL NETWORK MODEL FOR THE OPTIMIZATIN OF ARBITRARY CONVEX FUNCTIONS WITH LINEAR CONSTRAINTS
-
摘要: 該文提出了線性約束條件下任意凸函數(shù)的神經(jīng)網(wǎng)絡(luò)優(yōu)化模型,所構(gòu)造的能量函數(shù)的平衡點(diǎn)即為原問題的最優(yōu)解,克服了傳統(tǒng)的神經(jīng)網(wǎng)絡(luò)優(yōu)化方法所存在的問題,網(wǎng)絡(luò)是全局穩(wěn)定的,并能收斂到最優(yōu)點(diǎn),計算機(jī)仿真結(jié)果證明了本文方法的有效性。Abstract: This article presents a neural network model for the optimization of arbitrary convex functions with linear constraints. The equilibrium point of the energy function constructed is the optima] solution of the original problem. The problems, which would arise in conventional neural network optimization methods, are overcome. The neural model is globally stable and can converge to the optimal point. The computer simulation results verify the effectiveness of the method.
-
S. Haykin, Adaptive Filter Theory, 3rd ed. NJ: Prentice-Hall, 1996, Chapter 5.[2]J.B. Schodorf, D. B. Williams, A constrained optimization approach to multiuser detection, IEEE Trans. on SP, 1997, SP-45(1), 258-262.[3]宋榮方,畢光國,CDMA系統(tǒng)中時空綜合干擾抑制的約束優(yōu)化模型及其神經(jīng)網(wǎng)絡(luò)實現(xiàn),電子學(xué)報,2001,29(4),475-478[4]闞超,基于神經(jīng)網(wǎng)絡(luò)的電信網(wǎng)DNHR算法及實現(xiàn)DNHR的有關(guān)協(xié)議,[碩士論文],南京,南京郵電學(xué)院,1991.[5]D.D. Tank, J. J. Hopfield, Simple neural optimization networks: An A/D converter, signaldecision and a linear programming, IEEE Trans. on CAS, 1986, 33(5), 533-541.[6]M.P. Kenney, L. O. Chua, Neural network for nonlinear programming, IEEE Trans. on CAS,1988, 35(5), 554-562.[7]A. Rodrguez, et al., Nonlinear switched-capacitor neural network for optimization problems, IEEETrans. on CAS, 1990, 37(3), 384-397.[8]陳開明,非線性規(guī)劃,上海,復(fù)旦大學(xué)出版社,199l,第2章.[9]宋榮方,畢光國,線性約束凸規(guī)劃神經(jīng)網(wǎng)絡(luò)新模型,信號處理,2001,17(2),104-109. -
計量
- 文章訪問數(shù): 2456
- HTML全文瀏覽量: 124
- PDF下載量: 619
- 被引次數(shù): 0
下載:
