共查询到20条相似文献,搜索用时 265 毫秒
1.
2.
结构优化的RBF神经网络学习算法 总被引:9,自引:0,他引:9
文章提出了一种自动“删减”隐层神经元的RBF神经网络学习算法。模拟结果表明,该算法训练的RBF网络不仅结构得以优化,同时性能良好,可能成功地应用于模式分类和时间序列预测问题中。 相似文献
3.
针对深度学习在SAR遥感图像地物分类检测中存在的问题,文章通过对基于深度学习的卷积神经网络(Convolutional Neural Network,CNN)进行优化改进,从而提高分类检测准确性。首先提出采用Leaky ReLU函数作为非线性整流函数,克服网络反向传播时梯度消失的问题;然后提出变步长动量梯度下降算法,加速网络收敛、减弱震荡,并避免网络陷入局部极小值。最后综合提出了"Leaky ReLU+变步长+动量梯度下降"的优化方法。通过实验,验证了文章所提出方法的有效性和准确性。 相似文献
4.
基于广义径向基函数神经网络的非线性时间序列预测器 总被引:5,自引:0,他引:5
该文对传统的径向基函数(RBF)神经网络的结构和学习算法进行了总结,并在此基础上提出了广义径向基函数模型概念,使这种网络具有更好的应用灵活性与可扩充性。文章基于Mackey-Glass造血模型方程的数值解数据,对此广义模型与现有的RBF模型和梯度径向基函数(GRBF)模型对一笥时间序列预测问题的应用结果进行了比较与讨论,显示出这种广义模型的应用有效性。 相似文献
5.
6.
传统的自适应方法一般采用梯度下降法搜索最佳权,但梯度法的性能对步长敏感。本文介绍一种全新的、无需步长选择的稳定收敛的FIR方法。该方法采用几何中心法进行递推。仿真结果表明由该方法导出的算法性能很好。 相似文献
7.
8.
利用深度展开的方法来设计深度神经网络在如今成为了一种经典的优化方法。文章提出了一种新的基于深度学习和压缩感知的重构算法用于序列信号重构。该模型设计理念是通过用近端梯度下降方法来对模型做迭代展开。在MNIST数据集上的实验表明,该模型表现要优于一些先进的基于压缩感知的模型以及其他基于循环神经网络的模型。 相似文献
9.
10.
11.
LinJiayu LiuYing 《电子科学学刊(英文版)》2002,19(3):255-258
A new algorithm to exploit the learning rates of gradient descent method is presented, based on the second-order Taylor expansion of the error energy function with respect to learning rate, at some values decided by "award-punish" strategy. Detailed deduction of the algorithm applied to RBF networks is given. Simulation studies show that this algorithm can increase the rate of convergence and improve the performance of the gradient descent method. 相似文献
12.
13.
New learning algorithms for an adaptive nonlinear forward predictor that is based on a pipelined recurrent neural network (PRNN) are presented. A computationally efficient gradient descent (GD) learning algorithm, together with a novel extended recursive least squares (ERLS) learning algorithm, are proposed. Simulation studies based on three speech signals that have been made public and are available on the World Wide Web (WWW) are used to test the nonlinear predictor. The gradient descent algorithm is shown to yield poor performance in terms of prediction error gain, whereas consistently improved results are achieved with the ERLS algorithm. The merit of the nonlinear predictor structure is confirmed by yielding approximately 2 dB higher prediction gain than a linear structure predictor that employs the conventional recursive least squares (RLS) algorithm 相似文献
14.
传统的RBF(Radial Basis Function)神经元基函数通常把高斯类型与单一宽度作为每个神经元的激活函数,这些特性限制了网络神经元的性能,特别是在处理复杂的非线性建模问题上.为了克服这个限制,本文应用了具有类似RBF网络,但激活函数不同-超基函数HBF(Hyper Basis Function)的网络.结合RBF网络,分析了HBF网络的结构、基函数形式及基函数对网络的影响,利用决策树算法计算了网络中心.在此基础上,提出了一种基于HBF神经网络的自适应观测器设计方法,并通过引入Lyapunov函数,证明了这种观测器设计方法的稳定性;最后通过仿真验证了这种HBF神经网络观测器能很好地观测系统的状态值. 相似文献
15.
人工神经网络( ANN)进行建模时通常需要准备大量的数据样本,同时网络结构一般都比较复杂;而采用支持向量机( SVM)进行建模时,不同核函数有不同的效果,各有利弊,且选取SVM模型参数的理论支撑尚不完整。为了解决这些问题,提出了一种基于混合核函数的支持向量机来改善来波到达角( DOA)的估计性能,并结合二进制粒子群算法( PSO)来对混合核函数进行参数寻优。该混合核函数由全局核函数和局部核函数构成,提高了SVM的泛化能力和学习能力。首先通过拟合多项式函数,验证了该混合核SVM的有效性。将该方法用于DOA估计建模,在不同信噪比和快拍数下,通过与径向基函数( RBF)神经网络、基于各单一核函数的SVM和MUSIC算法预测结果对比,混合核SVM均方差有所降低,提高了DOA估计的精度且有更好的稳定性。 相似文献
16.
This paper studies three related algorithms: the (traditional) gradient descent (GD) algorithm, the exponentiated gradient algorithm with positive and negative weights (EG± algorithm), and the exponentiated gradient algorithm with unnormalized positive and negative weights (EGU± algorithm). These algorithms have been previously analyzed using the “mistake-bound framework” in the computational learning theory community. We perform a traditional signal processing analysis in terms of the mean square error. A relationship between the learning rate and the mean squared error (MSE) of predictions is found for the family of algorithms. This is used to compare the performance of the algorithms by choosing learning rates such that they converge to the same steady-state MSE. We demonstrate that if the target weight vector is sparse, the EG± algorithm typically converges more quickly than the GD or EGU± algorithms that perform very similarly. A side effect of our analysis is a reparametrization of the algorithms that provides insights into their behavior. The general form of the results we obtain are consistent with those obtained in the mistake-bound framework. The application of the algorithms to acoustic echo cancellation is then studied, and it is shown in some circumstances that the EG± algorithm will converge faster than the other two algorithms 相似文献
17.
18.
19.
Neural-network-based predictive learning control of ram velocity in injection molding 总被引:3,自引:0,他引:3
S.N. Huang K.K. Tan T.H. Lee 《IEEE transactions on systems, man and cybernetics. Part C, Applications and reviews》2004,34(3):363-368
In this paper, we develop a predictive learning controller for ram velocity of injection molding based on neural networks. We first introduce a model of describing the injection molding, including the time horizon and the batch index. The feedback control plus biased function is proposed for controlling this plant. More specifically, a radial basis function (RBF) network is used to approximate the biased function based on the time horizon. The weights in the RBF are determined by a predictive control scheme based on the batch index. For this algorithm, relevant convergence is investigated. Simulation results reveal that the proposed control can achieve our claims. 相似文献