First, the usual ways that are employed to choose the number of RBFNN's hidden layer nodes are analyzed and compared.
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。
Provided with the Algorithm to determine the pre-possessing of sample data, learning rate, momentum factor, the Number of Hidden Layer Nodes, etc.
给出了样本数据的预处理以及学习因子、动量系数、隐含层结点数等诚然定方法。
As for it, by improving learning algorithm of traditional RBF neural network, a new dynamic cluster-based self-generated method for hidden layer nodes is proposed.
对此，本文改进了R BF神经网络的学习算法，提出了一种基于聚类的动态自生成隐含层节点的思想。
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.
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 output of each input layer node is fed to each of six hidden-layer nodes, which in turn feed three output nodes.
再将各个输入层节点的输出 提供给6 个隐藏层节点，这些隐藏层节点将依次提供给3 个输出接点。
With the pull methodology, individual nodes have no way of knowing if they are in the input, hidden, or output layer.
使用pull方法则无法知道节点究竟位于输入层、隐藏层还是输出层。
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.
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。
Here I give some references to the selection of the number of hidden-layer nodes and learning rate.
在这里我们对于隐含层节点数选择、学习速率选择等问题提出一些参考意见。
The main problems in designing a RBFNN depend on fixing the nodes of the hidden layer, the parameters of the centers and the linear weights.
设计中存在的主要问题包括隐层神经元数、中心和半径的确定，以及网络权值的训练。
The model consists of three neuron layers: input layer with 12 nodes, output layer with 22 nodes and hidden layer.
BP神经网络模型的输入层设12个结点，输出层设22结点，设一层隐含层。
The model consists of three neuron layers: input layer with 12 nodes, output layer with 22 nodes and hidden layer.
BP神经网络模型的输入层设12个结点，输出层设22结点，设一层隐含层。
应用推荐