搜索资源列表
dltd
- 采用动量梯度下降算法训练BP网络。在本源码中,训练样本定如下:p=[-1 -2 3 1 -1 1 5 -3] 目标矢量为t=[-1 -1 1 1]-Gradient descent algorithm using momentum BP network training. In this source, the training sample set as follows: p = [-1-2 3 1 -1 1 5-3] target vector for t = [-1-1 1 1]
mean-shift
- Mean Shift 这个概念最早是由Fukunaga等人[1]于1975年在一篇关于概率密度梯度函数的估计中提出来的,其最初含义正如其名,就是偏移的均值向量,在这里Mean Shift是一个名词,它指代的是一个向量,但随着Mean Shift理论的发展,Mean Shift的含义也发生了变化,如果我们说Mean Shift算法,一般是指一个迭代的步骤,即先算出当前点的偏移均值,移动该点到其偏移均值,然后以此为新的起始点,继续移动,直到满足一定的条件结束.-Mean Shift concept
A-new-SVM-method-based-on-gradient
- 基于支持向量机选择确定决定分类最优分界面的支持向量样本,基于这些样本中各个变量在基坐标上投影进行变量选择-Selection based on support vector machine (SVM) to determine the optimal boundary decision classification support vector of the sample, based on the sample of each variable on the base coordinate p
DeepLearnToolbox_CNN_lzbV3.0
- CNN - 主程序 参考文献: [1] Notes on Convolutional Neural Networks. Jake Bouvrie. 2006 [2] Gradient-Based Learning Applied to Document Recognition. Yann LeCun. 1998 [3] https://github.com/rasmusbergpalm/DeepLearnToolbox 作者:陆振波 电子