数据中心和扩展常数调整过程中还引入了隐节点的合并操作和删除操作。
Hidden units combination and deletion in the process of adjusting data centers and spread constants are also introduced.
结构学习确定了表示了模糊规则和模糊分段数的连接类型以及隐节点数目。
The structure learning decides the proper connection types and the number of hidden units which represent fuzzy logic rules and the number of fuzzy partitions.
对于常用的三层结构的神经网络，隐节点数目的确定一直是个难题，至今无定论。
For the commonly used three-layered neural network, how to select the number of the hidden nodes is always a real problem.
使用BP算法训练多层网络的速度很慢而且事先难于确定隐节点和隐层的适当数目。
Training a multilayer neural net by BP algorithm is slow and it is difficult to choose the number of hidden units and layers in advance.
根据神经网络的特性及其运作方式，将日常广泛使用的黄金分割原理用于网络隐节点个数的确定中。
According to the characteristics and working manners of neural network, the golden section principle which is used in living abroad is introduced to confirm the node of hidden layer of network.
介绍了系统构成原理和用于废水紫外光谱图识别的多层前向神经网络的设计， 分析了含有不同隐节点数的前馈网络的精度；
The structure of the system and the design of the multiple feedforward neural network used for identification of spectrogram of wastewater are discussed.
然后，给出了一种可对上述三层感知器进行压缩的隐节点的压缩方法，它可以推广到三层以上的感知器和节点激发函数不同的情形。
Then, a method is presented to compress the number of hidden nodes, which can be extended to more than three layer perceptrons and to the case of using different activation functions.
R BF网络的设计问题就是关于网络隐节点数和隐层节点RBF函数中心、宽度和隐层到输出层的权值的性能指标的最小化问题。
The RBF network configuration is formulated as a minimization problem with respect to the number of hidden layer nodes, the center locations and the connection weights.
每种服务还隐式或显式地表示节点之间的信息传递，并且可能被描述为一个消息或运作。
Each service, implicitly or explicitly, also represents the transfer of information between nodes and may be characterized as a message or operation.
当前节点就像是一个隐式参数。
考察了隐层节点数对网络收敛速度、识别正确率的影响以及学习率对收敛速度的影响，改进了网络训练算法。
The influence to convergent speed and recognition accuracy of both concealed layer node count and the learning rate is considered.
首先对目前常用的RBF网络的隐层节点数的选择办法进行了分析，并指出它们的优点和不足。
First, the usual ways that are employed to choose the number of RBFNN's hidden layer nodes are analyzed and compared.
总结了正交法的应用研究，提出用正交化方法来确定前馈神经网络的结构，包括隐层数、节点数以及网络训练步数。
Based on summarizing of the application of onhogonal method, an onhogonal method for deciding the number of hidden layers, neurons and the training step of neural networks is presented.
医学知识存储在症状与疾病的模糊关系上。推理时使用模糊关系合成的方法。对基于规则的神经网络方法，从规则集中自动构造网络的结构，确定隐层节点数和连接权值。
The clinic knowledge is stored in the fuzzy relations between disease condition and the all correlative disease, and It can get the clinical diagnosis from these fuzzy relations by synthesizing.
医学知识存储在症状与疾病的模糊关系上。推理时使用模糊关系合成的方法。对基于规则的神经网络方法，从规则集中自动构造网络的结构，确定隐层节点数和连接权值。
The clinic knowledge is stored in the fuzzy relations between disease condition and the all correlative disease, and It can get the clinical diagnosis from these fuzzy relations by synthesizing.
应用推荐