小神经

A theorem shows that if we apply the FNN with its algorithm in the control of the systems above mentioned, the static error will be small arbitrarily as long as the parameter δ in hypercylinder is small enough. The feasibility and the control effectiveness of the method are examined through simulation example of nonlinear dynamic system.

将基于超柱体聚类的模糊神经网络及其学习算法用于不可逆的非线性系统模型Ⅱ的控制中，定理表明，静态误差可以任意小，只要聚类的底面直径足够小。

The experimental results show that temperature error and non-linearity of silicon piezoresistive pressure sensor can be reduced markedly.

本文针对其缺点，提出了以正交的局部函数——小波函数作为激励函数的小波神经网络对硅压阻式压力传感器的温度误差进行补偿。

Methods 35 patients with the homonymy leg soft tissue defects were treated with the flap. The largest flap size was 16 cm×11 cm, the smallest flap was 7 cm×6 cm. The small saphenous vein were inosculated with the recipient site vein in 14 patients, while not in the other 21 cases.

应用腓肠神经营养血管逆行岛状皮瓣修复同侧下肢软组织缺损35例，皮瓣面积最大16 cm×11 cm，最小7cm×6 cm，其中将小隐静脉与受区静脉吻合14例，未吻合静脉21例。

The simulation results show that the novel BP wavelet neural network based on IPSO not only has the good local property of wavelet analysis and the learning and classification capability of artificial neural network, but also has the fast global searching advantage of particle swarm optimization algorithm.

实验结果表明，基于改进的粒子群优化算法的BP小波网络不仅具有小波分析良好的局部特性以及神经网络的学习、分类能力，而且具有粒子群优化算法全局快速寻优的特点。

The Recursive Least Square based on Lethe gene, Partial Least Square, BP Nerve Network,which are wide applied in process control, are discussed detailedly respectively. The characteristic and their domain applicable fields of each model and their mend models are systematically analysed.

对在过程控制领域广泛应用的渐消记忆递推最小二乘法、偏最小二乘法和BP 神经网络等建模方法进行了详细的讨论，并对每种建模方法及其改进算法的特性、应用范围进行了深入的分析。

Setting forth the realization method by hardware for searching minimal cutset of a graph with N-SearCut model. Then this method affords theory and practice fundament for solving this puzzle of searching for minimal cutset in reliability evaluation of power system.

提出了运用N-SearCut神经网络模型搜索图最小割集的全硬件实现方法，为更理想地解决网络可靠性评估中出现的最小割集搜索这一瓶颈问题提出了新的思路，提供了理论和实践依据。

This thesis discussed the recursive least square algorithm , M-P pseudo-inverse algorithm and recursive orthogonal least square algorithm for the RBPNNs.

文中讨论了递推最小二乘算法、M-P伪逆算法和递推正交最小二乘算法用于径向基概率神经网络的训练问题。

The first one focuses upon the fundamental theory and methods of system identification, including the basic concepts of system description and identification,review of matrix theory, stochastic process and pulse response of linear systems; the first principle models for lumped and distributed parameter systems; modeling of bioreactions; auto regressive moving average model; weighted least square and regressive weighted least square for parameter estimation of ARMA model; Runge-Kutta and Simplex methods; an example of BPNN application; as well as Kalman Filter.

第一部分包括知识驱动建模、数据驱动建模、参数估计和状态估计的基础理论和方法。具体为：(1)系统辨识和系统描述的基本概念，包括矩阵论、随机过程、线性系统的脉冲响应函数等基础知识回顾；(2)基于动态物料和能量衡算的集总参数、分布参数对象的知识驱动建模方法；(3)生物反应系统的建模方法；(4)自回归移动平均模型；(5) ARMAX模型参数的加权最小二乘参数估计一次性算法和递推算法，相应的统计性质；(6)龙格库塔法和单纯形法；BP神经网络应用实例；(7)卡尔曼滤波器，及其与加权最小二乘参数估计递推算法的对比。

Results Denatured necrosis occurred on the surface of hypothalamic periosteum with no cells and there was a large amount of starchy bodies and hydrops in foci with angiectasis of choroid plexus and necrosis and calcification in tunicaintima of vesicles,and mitochondria in the nerve synapse disappeared and part of anteroposterior membranes ...

结果 慢性SZ患者下丘脑部室管膜表面变性坏死、无细胞，病灶中有大量淀粉样小体和水肿，脉络丛血管扩张，管壁内膜有坏死和钙化；神经突触内大部分突触小泡和线粒体消失，部分前后膜模糊不清。

Acorrding to the character that wavelet transform technique can localize thetime-domain and frequency-domain, it can focalize any detail of signals and can recognize theabrupt signal and nostationary signal. The characteristics of typical fault for the centrifugalcompressor rotor are extracted by wavelet transform, and the characteristics vector is foundedby using energy as element.

通过小波变换技术对时域和频域同时具有良好的局部化性质，可以聚焦到信号的任意细节，对突变信号和非平稳信号具有很强的识别能力，利用小波包变换对离心压缩机转子典型故障的振动信号进行特征提取，并以&能量&为元素，构造离心压缩机故障信号的特征向量，以便神经网络识别。

The split between the two groups can hardly be papered over.

这两个团体间的分歧难以掩饰。

This approach not only encourages a greater number of responses, but minimizes the likelihood of stale groupthink.

这种做法不仅鼓励了更多的反应，而且减少跟风的可能性。