CAGen

说明：  近完美重构多相滤波器组实例，包含分析滤波器，综合滤波器，其中原型滤波器系数可调整，以及重构错误的仿真。(Near perfect reconstruction polyphase filter example, contains analysis filters, synthesis filters, which can adjust the prototype filter coefficients, and the reconstruction error is simulated.)

无网格EFG一维matlab程序 可参见张雄无网格专著(Meshless EFG one-dimensional matlab program can be found in Zhang Xiong meshless monograph)

经典的music算法程序，进行波达方向估计，利用空间谱函数进行谱峰搜索，对信号源的波达方向估计(Classical music algorithm for direction of arrival estimation, the use of space spectral function spectral peak searching, the signal source DOA estimation)

股市预测的matlab代码，可作为入门的程序，按需要自行修改(Stock market prediction of matlab code, and can be used as the basic procedures, according to the need to modify)

MATLAB智能算法30个案例分析,本书采用案例形式，以智能算法为主线，讲解了遗传算法鱼群算法等。(Analysis of 30 Cases of Intelligent Algorithms in MATLAB.This book uses the case form, takes the intelligent algorithm as the main line, explains the genetic algorithm fish swarm algorithm and so on.)

此算法为用于解反问题的lsqr算法，对Ax=b，输入矩阵A，列向量b，以及迭代步数，求得列向量x(This algorithm is used for solution of the inverse problem lsqr algorithm, Ax = b, the input matrix A, the column vector b, as well as the number of iterative steps, to seek the column vector x)

汽车被动悬架模型，半主动正在整，稍后上传(Car passive suspension model, semi-active being whole, later upload)

深度神经网络在函数近似中表现优越，然而需要从头开始训练。另一方面，贝叶斯方法，像高斯过程（GPs），可以利用利用先验知识在测试阶段进行快速推理。然而，高斯过程的计算量很大，也很难设计出合适的先验。本篇论文中我们提出了一种神经模型，条件神经过程（CNPs），可以结合这两者的优点。CNPs受灵活的随机过程的启发，比如GPs，但是结构是神经网络，并且通过梯度下降训练。CNPs通过很少的数据训练后就可以进行准确的预测，然后扩展到复杂函数和大数据集。我们证明了这个方法在一些典型的机器学习任务上面的的表现和功能，比如回归，分类和图像补全(Deep neural networks perform well in function approximation, but they need to be trained from scratch. On the other hand, Bayesian methods, such as Gauss Process (GPs), can make use of prior knowledge to conduct rapid reasoning in the testing stage. However, the calculation of Gauss process is very heavy, and it is difficult to design a suitable priori. In this paper, we propose a neural model, conditional neural processes (CNPs), which can combine the advantages of both. CNPs are inspired by flexible stochastic processes, such as GPs, but are structured as neural networks and trained by gradient descent. CNPs can predict accurately with very little data training, and then extend to complex functions and large data sets. We demonstrate the performance and functions of this method on some typical machine learning tasks, such as regression, classification and image completion.)

光电综合实验，南邮的，必须的，肯定的，很好的，很强的(very good)

说明：  图像浮雕化matlab程序 就好像《康熙大帝》中浮雕效果，对不同图像只要修改文件名(relief images of Matlab programs like the "Emperor Kangxi" relief and the effect of different image file name as long as the changes)