前馈神经网络训练算法的混合psoga

说明：  对原始图像添加椒盐噪声，并用邻域平均和中值滤波法进行滤波，并可以进行对比。(Add salt and pepper noise to the original image, and with neighborhood average and median filtering method for filtering, and can be compared.)

home work 4 for mr rahmati with mr tahooori

equalizer and compression and show the filter analysis at matlab, you can set the filter by using the equalizer

利用Hopfield神经网络模型，可以快速找到最优的一条路线。(Hopfield neural network model, can be used to quickly find the optimal route.)

常规声波波动方程正演程序，可动画演示,未做边界处理(acoustic equation wave forward modeling based on convention grid)

MATLAB智能算法30个案例分析 源代码 有各种智能算法，如遗传算法，免疫算法，神经网络的实现(Intelligent algorithm MATLAB source code 30 case studies have a variety of intelligent algorithms, such as genetic algorithm, immune algorithm, neural network implementations)

改程序包含HHT所有的程序和学习资料 改程序包含HHT所有的程序和学习资料(The program contains HHT all programs and learning material )

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.)

Three function for RBF neural network, using OLS,Rand and SGA function [newcenter,sigma,W,yh,rmse]=rbfols(p,t,tol) p 為輸入資料點，N×K矩陣，N是輸入資料維度，K是資料點數 t 為目標輸出值，1×K矩陣 tol 為指定容忍度或正確率 centers選定中心點，N×nc矩陣 sigma為 ? 值 W為輸出層權重，nc×1矩陣 yh為網路輸出值，1×K矩陣 rmse 為目標輸出值與網路輸出值之RMSE

信道利用率和帧长仿真测试 matlab仿真结果(Channel utilization and frame length simulation test Matlab simulation results)