It should be pointed out that the constructive algorithm does not depend on the nature of the strategy determined by parameters , and that the constructive algorithm is also suitable for both level track and non - zero gradient track theoretically 本文还给出一种基于迭代序列的构造性算法,该算法调用了基本计算过程但不需要确定参数对入和。所对应的运行方案的本质,从理论上来说它也是既适合水平轨道又适合带有坡度轨道的。
This paper researches the three - layered b - spline neural network , which is commonly used in engineering and presents a constructive algorithm for selecting the number of the hidden nodes . it is proved that the proposes algorithm can be used to build a b - spline neural network with minimum hidden nodes to approximate any continuous function defined on compact set to a prescribed accuracy 本文研究了工程上常用的三层b样条神经网络,采用构造性的方法证明了b样条神经网络的全局逼近能力,并且给出了构造几乎最小隐节点的算法,从而在理论上为b样条神经网络的使用提供了依据。