最佳化B-spline神經網路近似非線性函數-使用基因演算法

dc.contributor 國立臺灣師範大學電機工程學系 zh_tw
dc.contributor.author 張貞觀 zh_tw
dc.contributor.author 王偉彥 zh_tw
dc.date.accessioned 2014-10-30T09:28:24Z
dc.date.available 2014-10-30T09:28:24Z
dc.date.issued 2003-03-14 zh_TW
dc.description.abstract 在本文中,吾人提出一種利用最佳化B-spline類神經網路來近似非線性函數的方法。傳統的B-spline函數是固定基礎函數,然而本文是利用基因演算法來對 B-spline類神經網路的基礎函數及控制點做最佳化的調整。而且基因演算法可以藉由突變的運算,跳脫一般學習法則(如梯度下降法)在學習過程中可能會落入區域極值,無法找到系統的最佳值的問題。染色體由實數的方式組成,包括了B-spline類神經網路中的Knot向量及控制點。藉著B-spline區間調整的特性,使系統作細微的調整。最後以模擬例子驗證本論文方法的功效。 zh_tw
dc.description.abstract In this paper, we propose an optimal B-spline neural network to approximate a nonlinear function. Traditionally, a B-spline function has fixed-form blending functions. Genetic algorithms are used to optimize the blending functions and the control points of B-spline neural networks. The mutation operator in genetic algorithms can avoid falling into local minimum during the learning process. Chromosomes include the knot vectors and the control points of a B-spline neural network. Since the local tuning property, the fine-tuning ability of a B-spline neural network can be obtained. Finally, the simulation results demonstrate the effectiveness of the proposed method. en_US
dc.identifier ntnulib_tp_E0604_02_074 zh_TW
dc.identifier.uri http://rportal.lib.ntnu.edu.tw/handle/20.500.12235/32051
dc.language chi zh_TW
dc.relation 2003中華民國自動控制研討會 zh_tw
dc.relation 2003 Automatic Control Conference, pp. 1274-1278 en_US
dc.subject.other 類神經網路 zh_tw
dc.subject.other 向量 zh_tw
dc.subject.other 基因演算法 zh_tw
dc.subject.other 非線性函數 zh_tw
dc.subject.other 最佳化 zh_tw
dc.subject.other 模擬 zh_tw
dc.subject.other Neural network en_US
dc.subject.other Vector en_US
dc.subject.other Genetic algorithm (GA) en_US
dc.subject.other Nonlinear function en_US
dc.subject.other Optimization en_US
dc.subject.other Simulation en_US
dc.title 最佳化B-spline神經網路近似非線性函數-使用基因演算法 zh_tw
Files
Collections