matlab中替代数据法子函数 surrogate

《精通matlab》（张志勇北航）。内容详尽，是进一步学习matlab较好的工具(" Proficient in matlab" (Zhang Zhiyong Beihang). Detailed, is a good tool for further learning matlab)

温柔的形变模型分类器和两个不同的weak-learners决定树桩和感知。 问题是进行多层次的one-vs-all策略(Gentle AdaBoost Classifier with two different weak-learners : Decision Stump and Perceptron. Multi-class problem is performed with the one-vs-all strategy)

This software is based simulink, it shows the turbo encoder and decoder using app

均匀圆阵仿真:m=8 阵元数 azimuth=[-55 0 40] 方位角 p=length(azimuth) 信号源个数 snap=1000 最大快拍数 drl=0.5 圆阵半径与波长之比 snr=15 信噪比dB 流程：1、构造信号2、构造噪声阵列流型矩阵3、观测信号4、观测信号协方差矩阵5、求解特征值与特征向量6、显示图谱。(The uniform circular array simulation: m = 8 element azimuth = [-55 0 40] azimuth p = length (azimuth) number of source snap = 1000 maximum number of snapshots drl = 0.5 ratio of the radius of the circular array wavelength snr = 15 SNR dB process: 1, constructed signal structure noise array manifold matrix 3, the observed signals observed signals covariance matrix 5 eigenvalue and eigenvector 6, display the map.)

高斯过程分类程序，运用拉普拉斯近似来实现二分类和多分类功能。(Implements Laplace s approximation for binary and multiclass classification.)

Hermite差值函数算法，输入两端点的函数值以及导数，输出是差值函数。(Hermite difference function algorithm, the two end points of the input function values ​ ​ and derivatives, the output is a function of the difference.)

迭代法求解线性方程组，首先将方程组AX=B中未知数X给定，计算出矩阵B。然后把矩阵B带入，利用雅各比迭代法反求X(Iterative method for solving linear equations, the first of equations AX = B will be in the unknown X given to calculate the matrix B. Then the matrix B into the use of Jacobi iterative method of reverse X)

一维灰度矩，用matlab进行编程，输入为一维灰度序列，输出为边缘值。不能直接处理图像！但有学习研究价值。(One-dimensional gray moment, using matlab programming for one-dimensional gray-scale input sequence, the output value for the edge. Can not directly deal with the image! But learning research value.)

abaqus用户自定义单元UEL程序实例(Abaqus user-defined units of education-the application instance)

NFC NDEF Arduino source and example