神经

One of the hot research issues of NN is to research into its capability of non-linear approximation.

神经网络的非线性逼近能力的研究是神经网络研究中的一个热点问题。

Methods The relationship of dynamic model′s input and output was analyzed and a basic structure of system identification model based on the principle of optimization in model reduction and the property of a function approximator to be composed of feed-forward networks was presented.

分析了控制系统动态模型的输入、输出关系，依据模型等效的最优化原理和神经网络任意逼近有限不连续函数的性质，提出神经网络辨识模型的基本结构。

The characteristics of B|spline basis function is first discussed, based on which B|spline neural network is proved to be a universal approximator.

1引言对于一个给定的非线性函数，我们都知道用神经网络可以以任意的精度来逼近它，原因就是神经网络是全局逼近器［1］。

If, on the one hand, neuroimaging studies use a correlational approach which cannot offer a final proof for such claims, available neuropsychological data fail to offer a conclusive demonstration for two main reasons: they use tasks taxing both language and action systems; and they rarely consider the possibility that Broca's aphasics may also be affected by some form of apraxia.

一方面，如果神经影像学研究采用不能提供最终证据的相关性的方法，有效的神经心理学试验数据因下列两个原因未能提供结论性证据：他们过度使用的语言和行为系统；他们很少考虑Broca's失语症患者也可能被某种形式失用影响的可能性。

The procedures of determining confined aquifer parameters by BP neural network were introduced...

为说明BP神经网络求含水层参数的原理，本文以文献数据给出了基于非稳定流抽水试验的BP神经网络求承压含水层参数的过程。

Methods: 24 cases operated with AF fixated were followed up, eight cases associcated spinal cord compression had been opened lamina, analysis of the influencing factors of fracture healing was made, postoperative restoration of nerve symptom and high of the vertebral body as well as spinal physiological arcuation were evaluaed.

通过随访24例骨质疏松合并腰椎骨折采用AF内固定手术治疗的病人，其中8例伴有脊髓神经压迫症状者同时行椎板切开减压术，总结分析影响骨折愈合的因素，评价术后伤椎高度、脊柱生理弯曲以及脊髓神经功能恢复的情况。

At last, regeneration of artifical nerves was evaluated.

最后，对人胚雪旺细胞人工神经进行神经再生效果的评价。

This paper discusses the development situation of artificial neural network, and the neural network control theory.

本文首先论述了人工神经网络的发展概况和神经网络的控制理论。

The neural complex of ascidian Styela clava was observed by two histological methods, and the methionine-enkephalin in the neural complex of Styela clava was analyzed by the immunohistochemical S-ABC (strept avidin-biotin complex) technique,respectively.

采用甲苯胺蓝染色和Golgi镀银法对柄海鞘神经复合体的结构进行显微观察，并通过免疫组织化学方法对甲硫氨酸脑啡肽在神经复合体中的分布进行了研究。

By analyzing the distribution of the zeros to the transcendental characteristic equation associated with the trivial.solution,we obtain some- sufficient conditions on the stability and instability of the trivial solution.These results are generalized to n-unit neural networks by means of space decomposition in this Chapter.

在第二章中，我们讨论了不带自反馈与带自反馈的3元环状神经网络系统平凡解所对应超越特征方程的根的分布情况，确定了系统平凡解稳定与不稳定的充分条件，并利用空间分解的方法把相应的结果推广到n元环状神经网络系统。

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。