oneshot

说明：  自适应simpson算法，数值分析考试用的(Adaptive Simpson algorithm for numerical analysis test)

计算回测程序，多因子选股模型，单因子测试(Calculation of back - test program, multi - factor stock - picking model, the single factor test)

简单地实现了一、二、三维的K均值聚类，效果还不错，适合初步学习模式识别的同志们(Simple implementation of one, two, three - dimensional k-means clustering, the effect is not bad, it is suitable for the initial learning pattern recognition comrades)

分支界限费用矩阵的说明文档，非常实用,建议下载哦(Branch line cost matrix documentation, very practical, it is recommended to download Oh)

这是利用FFT分析相位差的程序，具有一定的参考价值！(This is done using FFT analysis phase of the program, has a certain reference value!)

贝叶斯分类实验 模式识别课程实验所用的源程序(Bayesian classifier experimental pattern recognition programs used in the experimental program)

基于声纳信息的粒子滤波算法,可以利用声纳信息和不完全环境信息通过该算法完成机器人的自定位过程,本例是在原有基础上的改进,(Particle filter algorithm based on sonar information can use sonar information and incomplete environment information to complete the self-localization process of robot. This example is an improvement on the original basis.)

多项式计算器，可以用于多项式的各种计算。(Polynomial calculator can be used for a variety of computing polynomials.)

用FORTRAN编制的交错网格化数值模拟程序，生成共炮点理论地震记录。(using FORTRAN compiled by the staggered grid of numerical simulation program to produce a total theoretical shot seismic record.)

基于经典的增广拉格朗日乘子法, 对求解一类带有特定结构（主要是针对凸规划）的非光滑等式约束优化问题, 我们提出、分析并测试了一个新算法. 在极小化增广拉格朗日函数的每一步迭代中, 该算法有效结合了带有非单调线性搜索的交替方向技术, 我们建立了算法的收敛性, 并用它来求解在带有全变差正则化的图像恢复问题.(Based on the classic augmented Lagrangian multiplier method, we propose, analyze and test an algorithm for solving a class of equality-constrained nonsmooth optimization problems (chiefly but not necessarily convex programs) with a particular structure. The algorithm effectively combines an alternating direction technique with a nonmonotone line search to minimize the augmented Lagrangian function at each iteration. We establish convergence for this algorithm, and apply it to solving problems in image reconstruction with total variation regularization.)