搜索资源列表
Least QuadraticFiter
- 最小二乘法进行执行拟合小程序，只要输入一系列（大于2个坐标点）的数据，与matlab直线拟合结果做过比较，结果比较吻合和皮实-least squares fitting method for the implementation of small programs, as long as the importation of a series (more than two coordinate points), and Matlab linear fitting results done ear
优化了的过关键点的光滑曲线拟合算法
- 该程序是离散点平滑程序,可实现对一组有序离散数据进行闭合和不闭合情况的情况.-that the procedure was discrete points smoothing procedures, to be able to achieve an orderly group discrete data for closure and closure of the situation.
Example4
- 采用贝叶斯正则化算法（抑制过拟合）提高 BP 网络的推广能力，采用两种训练方法， 即 L-M 优化算法（trainlm）和贝叶斯正则化算法（trainbr），用以训练 BP 网络；-Bayesian regularization algorithm (inhibition of over-fitting) to improve the generalization ability of BP network, using two training methods, that LM opti
PCA
- 在多变量统计中，数据有很强的相关性，对数据进行主成分分析，这样可以避免过拟合- Multivariate statistical data there is a strong correlation, principal component analysis of the data, and to avoid over-fitting
vbemgmm
- 在混合高斯模型参数估计方法上有很多方法，例如最大似然函数的EM算法，但是该算法容易出现过拟合，故本文提出了一个变分EM的算法来对参数进行估计，可以避免EM算法中的不足。 下面的示例文件中说明了使用下面的示例文件说明了用法 examplevbem，VBEM M示例文件 faithful.txt数据集为例(The parameters of Gauss mixture model estimation method has a lot of methods, such as the maxim