training database

Based on the local features, we calculate the Euclidean distances between the input face image and every face images in the original training database and the calculated distances are acted as the criteria of choosing the reasonable database.

基于提取到的人脸图像特征，我们分别计算输入人脸图像和原始训练库中每幅人脸图像之间的欧式距离，并将其作为挑选新的人脸训练库的标准。

A three-step method, based on the characteristic of large space structures, using the merit of some methods of damage orientation, combining mode curvature and neural network, which solves the problem of overabundance training database in neural network, is put forward.

根据大跨度空间结构的特点，利用各种损伤定位方法的优点提出了模态曲率和神经网络相结合的三步损伤定位法解决了神经网络法中训练样本的组合爆炸问题。

The training database, which is composed of the set of input-output data pairs, is updated after each sampling interval, and the learning-prediction is repeated thereafter.

在每一次采样时间后，由输入输出数据对构成的训练数据库将被更新，然后程序重复进行下一轮的预报.本系统的资料都储存在数据库里。

With the help of the training database, we can synthesize the local details according the structural information.

在训练库的辅助下，我们根据这些结构信息合成出局部细节。

Having no restriction of main memory and record number and attribute number of training database, the algorithm can output practice and accurate decision tree.

该算法没有训练数据库需存储于内存的限制，对训练库也没有记录个数及属性个数的限制，能生成简练、精确的决策树。

Due to the limited sample set of the training database, it is difficult for all the face images are included in the training sample under non-ideal conditions.

由于数据库中的训练样本集有限，所以很难把各种非理想情况下的人脸图像都包括在训练样本中。

Application-Oriented Talents Training Database Course System and Teaching Model Reform

面向应用型人才培养的数据库系列课程体系和教学模式改革探索