监督图像分割，使用马尔可夫随机领域

自适应共振神经网络可以实现自动学习与分类具有自适应的功能-adaptive resonance neural network can automatically learning and classification of adaptive function

这个是用来进行基频检测的，目前做的最好的应该数Paul的基频提取算法了，误差可以小于万分之五。该源代码的算法是我根据Paul的算法修改得到，省略了插值部分，所以误差在百分之五以内，但是在实际工作中已经足够了。-is for the frequency of detection, so the best should be the number of frequency Paul extraction algorithm, can be less than prior error. The source code for the algorithm is based on the algorithm Paul to be amended, omitted the interpolation part, the error within 5%, but the actual work has been sufficient.

神经网络与pid混合控制源程序，可以很好的解决非线性控制问题-Neural network and hybrid control pid source can be a very good solution to nonlinear control problems

用BP神经网络程序模拟销售预测，能对销售数据进行时间序列预测，采用VC实现-BP neural network simulation sales forecasts, sales data can be right for time series prediction, using VC

用Canny算子检测图像的边缘 P0404：图像的阈值分割 P0405：用水线阈值法分割图像 P0406：对矩阵进行四叉树分解 P0407：将图像分为文字和非文字的两个类别 P0408：形态学梯度检测二值图像的边缘 P0409：形态学实例――从PCB图像中删除所有电流线，仅保留芯片对象-with Canny operator to detect the edges in the image P0404 : image thresholding segmentation P0405 : water line threshold method image segmentation P0406 : matrix Quadtree P0407 : images into text and non-text of the two categories P0408 : morphological gradient detection Binary Image Edge P0409 : morphology example-- Images from the PCB to delete all current lines, retaining only chip targets

bp_算法~在bp_.cpp文件里~-11 bp_.cpp algorithm to the document ~

BP神经网络自适应步长训练算法，采用最小误差法，梯度下降法，自适应调节权值-BP neural network training anaysis, is realized by using error feed back, gradient descent applied updating of synaptic weights

用遗传算法解迷宫问题的实现与改进-genetic algorithm maze of achievement and improvement

MATHEMATICA 软件运用 The biggest similarity for tsp-MATHEMATICA software to use The biggest similarity for tsp