共查询到19条相似文献,搜索用时 109 毫秒
1.
2.
3.
依据RBF神经元模型的几何解释,提出一种新的构造型神经网络分类算法.首先从样本数据本身入手,通过引入一个密度估计函数来对样本数据进行聚类分析;然后在特征空间里构造超球面,以逼近样本点分布的几何轮廓,从而将神经网络训练问题转化为点集"包含"问题.该算法有效克服了传统神经网络训练时间长、学习复杂的缺陷,同时也考虑了神经网络规模的优化问题.实验证明了该算法的有效性. 相似文献
4.
二进神经网络的汉明图学习算法 总被引:1,自引:0,他引:1
二进神经网络的几何学习算法ETL必须分隔全部真顶点集合和伪顶点集合,且为一种穷举的算法。该文使用所定义的汉明图和子汉明图,给出了选择核心顶点的依据,组成和扩展子汉明图的方向和步骤,以及一个子汉明图可用一个稳层神经元表示的条件和权值、阈值的计算公式。所提出的二进神经网络汉明图学习算法可用于任意布尔函数;无需穷举并一定收敛,因而是快速的;对文献所举实例取得了较ETL算法结构更为优化的三层前向网络。 相似文献
5.
一种新颖的神经网络稳健估计方法 总被引:2,自引:0,他引:2
当神经网络应用于实际工程问题时,网络的训练数据集成或多或少都有噪声或异常值掺入其中,为了使网络具有更好的稳健性,文中根据稳健统计学原理,针对前馈神经网络(FNN)提出了一种稳健估计(RE)函数作为新的网络目标函数。 相似文献
6.
一种新的RBF神经元网络分类算法 总被引:1,自引:1,他引:1
为了改善对人工神经网络行为的认识和研究中的"黑匣子"式的难以处理的状态,基于RBF神经元模型的几何解释,提出了一种新的RBF神经网络分类算法,算法把RBF神经元看作是高维空间里的超球面,从而将神经网络训练问题转化为点集"包含"问题.同传统的RBF网络相比,算法能够自动地优化RBF网络中核函数的个数、中心和宽度,同时,省去了传统RBF神经网络输出层线性连接权的计算,简化了网络的学习过程,大大缩短了训练时间,并且通过实验证明了算法的有效性. 相似文献
7.
新的C RBF神经网络分类器的设计与实现 总被引:1,自引:0,他引:1
从RBF神经元的几何意义出发,提出了一种新的用于模式识别的C-RBF神经网络分类器.与传统RBF网络相比,该算法能够自动地优化RBF网络中核函数的个数、中心和宽度,且由于竞争神经元的引入,省去了传统RBF神经网络输出层线性连接权的计算,从而简化了网络的学习过程,大大缩短了训练时间. 相似文献
8.
二进神经网络逻辑关系判据及等价性规则提取 总被引:3,自引:0,他引:3
二进神经网络中提取知识主要体现为对输入输出逻辑关系的提取,而逻辑关系的表达方式分为蕴含性规则和等价性规则文中对比了蕴含性规则和等价性规则的差异;以KT方法为例,讨论了蕴含性规则在表达二进神经网络内在知识时,对某些具有明确逻辑意义的二进神经网络,并不是最清晰的表达方式.对这些逻辑关系,采用等价性规则可以简洁清晰地解决问题,所以对于二进神经网络神经元表达的逻辑关系建立可能的等价性规则提取方法是有意义的.CH判据是一种提取等价性规则的方法,但CH判据是充分性判据,对二进神经元的权系数有约束条件,因此不适用于任何学习算法的学习结果.为解决这些问题,文中研究了二进神经网络表达几类等价逻辑关系的充要性判据,并根据这些判据提出了提取等价性规则的WTA方法.在使用WTA方法时,必须预先对二进神经元进行必要的剪枝.文中证明了剪枝定理,并通过二个例子说明了用WTA方法进行规则提取的过程. 相似文献
9.
给出了快速收敛的离散二进小波神经网络的初始化,构造和权值确定的详细方法。并将这类小波神经网络应用于传感器的非线性校正,并给出了仿真实验结果。相对使用随机贪心算法训练的神经网络,快速收敛小波神经网络利用离散二进小波变换的便利,采用启发式的构造算法;具有构造过程复杂度低,构造完成后高度接近目标模型,训练次数少,并可有效避免陷入局部极小点的优点。有效解决了小波神经网络尺度和平移系数在训练时需对小波函数进行求导而影响网络收敛速度的问题。 相似文献
10.
给出了快速收敛的离散二进小渡神经网络的初始化.构造和权值确定的详细方法。并将这类小波神经网络应用于传感器的非线性校正,并给出了仿真实验结果。相对使用随机贪心算法训练的神经网络,快速收敛小波神经网络利用离散二进小波变换的便利,采用启发式的构造算法;具有构造过程复杂度低,构造完成后高度接近目标模型,训练次数少,并可有效避免陷入局部极小点的优点。有效解决了小波神经网络尺度和平移系数在训练时需对小波函数进行求导而影响网络收敛速度的问题。 相似文献
11.
Andrzej Rusiecki 《Neural Processing Letters》2012,36(2):145-160
Outliers and gross errors in training data sets can seriously deteriorate the performance of traditional supervised feedforward neural networks learning algorithms. This is why several learning methods, to some extent robust to outliers, have been proposed. In this paper we present a new robust learning algorithm based on the iterative Least Median of Squares, that outperforms some existing solutions in its accuracy or speed. We demonstrate how to minimise new non-differentiable performance function by a deterministic approximate method. Results of simulations and comparison with other learning methods are demonstrated. Improved robustness of our novel algorithm, for data sets with varying degrees of outliers, is shown. 相似文献
12.
一种鲁棒BP算法及其在非线性动态系统辨识中的应用 总被引:4,自引:0,他引:4
利用多层前馈神经网络的非线性建模特性,基于动态BP网络的串并联和并联模型,提出了一种高鲁棒性BP算法,与传统的BP算法相比,鲁棒BP算法有5个优点:(1)适合于非线性动态系统辨识,(2)辨识精度高;(3)不必内插所有训练样本;(4)具有高鲁棒性,能抵制过失误差和量测误差;(5)收敛速度得到了改进,因为错误差样本的影响得到了适度的抑制,把该算法用于非线性动态系统辨识,仿真结果表明此方法是有效的。 相似文献
13.
14.
15.
16.
17.
The annealing robust backpropagation (ARBP) learning algorithm 总被引:2,自引:0,他引:2
Chen-Chia Chuang Shun-Feng Su Chin-Ching Hsiao 《Neural Networks, IEEE Transactions on》2000,11(5):1067-1077
Multilayer feedforward neural networks are often referred to as universal approximators. Nevertheless, if the used training data are corrupted by large noise, such as outliers, traditional backpropagation learning schemes may not always come up with acceptable performance. Even though various robust learning algorithms have been proposed in the literature, those approaches still suffer from the initialization problem. In those robust learning algorithms, the so-called M-estimator is employed. For the M-estimation type of learning algorithms, the loss function is used to play the role in discriminating against outliers from the majority by degrading the effects of those outliers in learning. However, the loss function used in those algorithms may not correctly discriminate against those outliers. In the paper, the annealing robust backpropagation learning algorithm (ARBP) that adopts the annealing concept into the robust learning algorithms is proposed to deal with the problem of modeling under the existence of outliers. The proposed algorithm has been employed in various examples. Those results all demonstrated the superiority over other robust learning algorithms independent of outliers. In the paper, not only is the annealing concept adopted into the robust learning algorithms but also the annealing schedule k/t was found experimentally to achieve the best performance among other annealing schedules, where k is a constant and t is the epoch number. 相似文献
18.
Simulation based control of discrete event systems has been a potential approach to support decision-making in the manufacturing scenario. In this paper, a knowledge intensive simulation modelling approach for a discrete even system is investigated. Based on the proposed simulation model, a robust control mechanism is presented that is believed to add significant value to discrete event dynamic system. The algorithm utilises neural network feedforward control plus robust proportional derivative feedback control to achieve control performance and output stability. The novel simulation approach, as well as the proposed controller, is implemented in an Extend TM environment and the effectiveness and usefulness of the proposed controller are verified, industrially, in the hard disk drive assembly process, a significant component of the Singapore manufacturing economy. 相似文献
19.
A new algorithm is presented for training of multilayer feedforward neural networks by integrating a genetic algorithm with an adaptive conjugate gradient neural network learning algorithm. The parallel hybrid learning algorithm has been implemented in C on an MIMD shared memory machine (Cray Y-MP8/864 supercomputer). It has been applied to two different domains, engineering design and image recognition. The performance of the algorithm has been evaluated by applying it to three examples. The superior convergence property of the parallel hybrid neural network learning algorithm presented in this paper is demonstrated. 相似文献