共查询到20条相似文献,搜索用时 218 毫秒
1.
2.
前向神经网络的一种快速分层线性优化算法 总被引:4,自引:1,他引:3
本文利用数学分析的方法,提出了一种前向神经网络快速分层线性优化算法,其特点是:用新方法构造了各层的目标函数;无须计算Hessian矩阵,加快了算法的收敛速度.仿真实验表明,与传统算法如误差反传法或BP法和含势态因子(Momentum factor)的BP法以及现有的分层优化算法相比,新算法能加快收敛速度,并降低学习误差. 相似文献
3.
为了提高回转体圆度误差测量精度,基于差动技术,并利用小波变换过滤算法及圆度误差最小二乘法模型,提出一种基于扫描激光差动技术的圆度误差检测系统。采用分光镜分束的方法,形成两束光强调制信号,从原理上消除偏心误差的影响。通过对一标定零件进行圆度误差测量实验,设定不同的实验条件,偏心量分别为2~4 mm,5~7 mm、8~9 mm,所测得圆度误差值相差不超过0.62 μm。表明测量系统可以有效消除偏心误差,完成对回转体零件圆度误差的检测。解决了目前圆度误差检测中回转轴偏心量误差消除难度大、测量效率低等问题,为高精度检测提供了一种新思路。 相似文献
4.
徐科军 《电气电子教学学报》2016,(4)
线性度是一项非常重要的传感器静态性能指标,是评价和选用传感器的重要依据.在每种传感器工作原理的讲授中,都涉及到这项指标.本文介绍传感器线性度的重要性、计算要点、产生非线性的原因以及校正非线性的方法. 相似文献
5.
6.
一种基于单转位特征角的圆度误差分离方法研究 总被引:1,自引:0,他引:1
为提高光学标准球形状误差测量准确度,提出了 一种基于单转位特征角的圆度误差分离方法。本文方 法基于严格的数学原理,利用特征角在形状比较中参照作用,可完全回避开可能产生谐波抑 制的所有“盲 点”;通过一次转位,并分别将转位前后的采样数据进行傅里叶变换,在频域中实现 光学标准球圆度 误差和主轴径向回转误差的分离,再将分离后的数据变换到时域,可以在使分离后的信号在 进入滤波器之 前无任何信号损失,使得建模过程无任何原理误差,实现主轴径向回转误差和光学标准器 圆度误差的完 全分离。实验表明,当每周采样点数为1024、 转位特征角为21.09′时,分离后圆度误差包含所有频次的谐 波,无任何谐波抑制,表明光学标准球圆度误差与仪器主轴的回转误差得到严格分离。本文 方法不仅可以用 于超精密级光学标准球的圆度测量,而且可用于建立精度水平最高的理想的基/标准级圆度 测量系统。 相似文献
7.
8.
9.
10.
11.
12.
Chin Tsu Yen Wan-de Weng Yen Tsun Lin 《Industrial Electronics, IEEE Transactions on》2004,51(2):472-479
The software simulation as well as the hardware implementation of equalizers for transmissions through nonlinear communication channels based on artificial neural networks structure is presented in this paper. We consider four-quadrature-amplitude-modulation technique as an example and compare the performance of two different structures of equalizer, namely, the linear least-mean-square-based equalizer (LIN) and the functional link artificial neural networks (FLANN). The learning curve and symbol error rate for the two structures are respectively evaluated by computer simulation. Besides, the systems have been implemented using field-programmable-gate-array devices. As FLANN uses functions to expand the dimensionality of the input signals, it has about the same system complexity as LIN. But FLANN can achieve fast processing speed under parallel processing structure. Simulation results have demonstrated that FLANN presents much better error performance than LIN, especially when the communication channel is highly nonlinear. 相似文献
13.
Global asymptotic and robust stability of recurrent neural networks with time delays 总被引:4,自引:0,他引:4
In this paper, two related problems, global asymptotic stability (GAS) and global robust stability (GRS) of neural networks with time delays, are studied. First, GAS of delayed neural networks is discussed based on Lyapunov method and linear matrix inequality. New criteria are given to ascertain the GAS of delayed neural networks. In the designs and applications of neural networks, it is necessary to consider the deviation effects of bounded perturbations of network parameters. In this case, a delayed neural network must be formulated as a interval neural network model. Several sufficient conditions are derived for the existence, uniqueness, and GRS of equilibria for interval neural networks with time delays by use of a new Lyapunov function and matrix inequality. These results are less restrictive than those given in the earlier references. 相似文献
14.
用劳埃德镜干涉原理进行圆度误差测量 总被引:4,自引:1,他引:3
提出一种应用线阵CCD自动测量圆度误差的新方法。论述了系统利用劳埃德镜干涉装置,通过线阵CCD图像处理系统自动测量圆度误差的工作原理及过程设计。测量结果表明,新的测量方法实现了圆度误差的实时精确在线测量。该测量系统具有一定的实用价值及较广阔的应用前景。 相似文献
15.
详细介绍一种基于神经网络的自学习非特定人语音识别方法,首次介绍一种语音识别知识的自动检验方法——LVV法,给出系统原理图和知识库的自动完善原理;介绍一种LEA判别法,实现梯度牛顿有效结合神经网络快速学习方法,并给出了实验结果。 相似文献
16.
17.
18.
解无约束极大极小问题的非对称神经网络算法 总被引:2,自引:0,他引:2
本文构造了一种新的非对称神经网络模型,用于求解极大极小无约束优化问题,并证明了非对称线性神经网络和非线性神经网络是整体Lyapunov稳定的,且收敛于对应的Lagrange方程的稳定点,计算机模拟的结果表明此方法是可行的,且具有良好的整体收敛性。 相似文献
19.
对称性是减少问题的自由度的一个强有力的工具.但在实际的应用中,系统变换操作的总数目将随系统维数的增加而急剧上升,这给高维系统对称性的计算带来了极大的不便,从而使得对称性方法的应用受到了很大的限制.本文以全互连结构的神经网络为例,提出一种基于遗传算法的搜索方法,在对称群Sn中寻找网络的对称置换操作,给出了计算机上的模拟结果,并与传统的遍历搜索方法作比较,分析了各自的优缺点.结果表明,这种基于遗传算法的搜索方法能够在极短的时间内找到网络的大部分对称置换操作.这使得对称性方法在高维神经网络研究及设计中的应用成为可能. 相似文献
20.
Fast adaptive digital equalization by recurrent neural networks 总被引:2,自引:0,他引:2
Parisi R. Di Claudio E.D. Orlandi G. Rao B.D. 《Signal Processing, IEEE Transactions on》1997,45(11):2731-2739
Neural networks (NNs) have been extensively applied to many signal processing problems. In particular, due to their capacity to form complex decision regions, NNs have been successfully used in adaptive equalization of digital communication channels. The mean square error (MSE) criterion, which is usually adopted in neural learning, is not directly related to the minimization of the classification error, i.e., bit error rate (BER), which is of interest in channel equalization. Moreover, common gradient-based learning techniques are often characterized by slow speed of convergence and numerical ill conditioning. In this paper, we introduce a novel approach to learning in recurrent neural networks (RNNs) that exploits the principle of discriminative learning, minimizing an error functional that is a direct measure of the classification error. The proposed method extends to RNNs a technique applied with success to fast learning of feedforward NNs and is based on the descent of the error functional in the space of the linear combinations of the neurons (the neuron space); its main features are higher speed of convergence and better numerical conditioning w.r.t. gradient-based approaches, whereas numerical stability is assured by the use of robust least squares solvers. Experiments regarding the equalization of PAM signals in different transmission channels are described, which demonstrate the effectiveness of the proposed approach 相似文献