| 1. | During training , a neural net inputs
在培训过程中，神经网络输入： |
| 2. | To reduce the dimensions of rbf network input vector farther , this thesis detects the 41 feature group by group
为了进一步减少rbf网络输入向量,本文对41个特征进行了分组检测。 |
| 3. | The debugging problems in applications development with network input and output data to software engineers is a big trouble
在软件开发中调试应用程序的网络输入和输出数据对于软件工程师们而言是一个非常麻烦的问题。 |
| 4. | A bp network learns by example , that is , we provide a learning set a big group of circles that consists of some input examples and the known - correct output for each case
该方法只需确定网络输入输出和约束条件,无需考虑中间过多的不确定因素,即可建立空间点与图像点的映射关系。 |
| 5. | In nntcs , we use artificial neural networks ( ann ) as the classifier . the recorded term frequencies form the original feature vector , matching with neurons in the input layer of ann one by one
系统使用神经网络作为分类器，特征词的词频组成原始特征向量，和神经网络输入层的神经元一一对应。 |
| 6. | 4 . using processed frequencies and first order modal dofs in a few points as network inputs , trained neural network gives excellent assessment results of a steel truss bridge
4 、本文以结构的低阶频率和少数节点的一阶振型分量，经预处理后作为神经网络输入，准确实现了对一钢析粱桥的损伤位置和损伤程度识别。 |
| 7. | This algorithm solves the problem of complex correlation by the node ' s design of neural network ' s input based on application of extensive ability effectively and effective study ability of itself
该方法有效地应用了神经网络的泛化能力以及自组织自适应的学习功能，且通过对网络输入结点的设计，能够很好地解决复杂航迹关联问题。 |
| 8. | After training , the bp can capture the inherent nonlinear mapping relationship held in sample set . while in operation , it can finish any nonlinear mapping from n - dim space of input to m - dim space of output
在运行阶段，当向网络输入训练时未见过的非样本时，它便能完成由输入的n维空间到输出的m维空间的任意非线性的正确映射。 |
| 9. | Neural network ' s training and damage detection influenced by input vectors which include the group of the first three frequencies or the group of the first three frequencies as well as the first modal shape , are studied
比较了仅以三阶频率作为神经网络输入向量和三阶频率及一阶振型组合作为网络输入向量对网络训练和损伤检测结果的影响。 |
| 10. | Factors including welding sequence being input of the network , and welding distortions being output can make the resulting network which is used for the model of welding distortion and its fast forecasting
以焊接顺序等因素作为网络输入，以钢结构板材凹凸变形为输出，训练生成网络焊接变形模型，可用于预测船舶钢结构焊接变形量的快速预测。 |
