A proposal of neural network architecture for nonlinear system modeling
A proposal of neural network architecture for nonlinear system modeling
复制标题
用于非线性系统建模的神经网络架构的建议
DOI：
10.1002/ecjb.20312
复制
发表时间：
2006
期刊：
影响因子：
--
通讯作者：
Kanya Tanaka
中科院分区：
文献类型：
--
作者：
Y. Mizukami;Y. Wakasa;Kanya Tanaka
本文提出了一种新的非线性系统建模神经网络体系结构。传统的神经网络建模方法存在以下问题：(1)耦合权值的内部表示难以分析；(2)权值初始化采用随机方案，无法再现；(3)对于没有训练样本的输入空间泛化能力不足。为了克服这些不足，本文提出了以下几种方法。首先是具有定域导数的s型函数的设计。第二种是权重初始化的确定性方案。第三个是权重参数的更新规则。基于两个输入一个输出的非线性系统进行了仿真。这些结果表明，初始误差小，建模误差小，收敛平稳，并且提高了分析内部表示的难度。©2006 Wiley期刊公司电子工程学报，2009,29 (1):1 - 4,2006；在线发表于Wiley InterScience （www.interscience.wiley.com）。DOI 10.1002 / ecjb.20312
This paper proposes new neural network architecture for nonlinear system modeling. The traditional modeling methods with neural network have the following problems: (1) difficulty in analyzing the internal representation, namely, the obtained values of the coupling weights, (2) no reproducibility due to the random scheme for weight initialization, (3) insufficient generalization ability for the input space in which no training sample exists. In order to overcome these deficiencies, the proposed method presents the following approaches. The first is the design of a sigmoid function with localized derivative. The second is a deterministic scheme for weight initialization. The third is an updating rule for weight parameters. Simulations were conducted based on several nonlinear systems with two inputs and one output. These results indicated small initial error, small modeling error, smooth convergence, and improvement of the difficulty in analyzing the internal representation. © 2006 Wiley Periodicals, Inc. Electron Comm Jpn Pt 2, 89(11): 40–49, 2006; Published online in Wiley InterScience (www.interscience.wiley.com). DOI 10.1002/ecjb.20312