上传列表：

eucliddis.rar - using euclidean distance to find the similarity between the seen and unseen images,2018-04-12 01:52:40,下载1次
class1.rar - using contourlet transform to extract the features of images and then using the neural classifier,2018-04-12 01:45:38,下载2次
pr11.rar - face recognition using PCA as feature extraction and ANN as classifier,2018-04-12 01:12:03,下载3次
pr13.rar - using wavelet transform to extract the feature images and then use the neural classifier for classification process,2018-04-12 01:09:28,下载1次
read_orl.rar - read an database images and arranged in a matrix,2018-04-12 01:04:30,下载1次
zainabtest.rar - decomposition and reconstruction using contourlet transform,2018-04-12 00:55:48,下载1次

近期下载：

PNN.rar - 概率神经网络(Probabilistic Neural Network)是由D.F.Speeht博士在1989年首先提出，是径向基网络的一个分支，属于前馈网络的一种。它具有如下优点：学习过程简单、训练速度快；分类更准确，容错性好等。从本质上说，它属于一种有监督的网络分类器，基于贝叶斯最小风险准则。
code-(2).rar - Using MATLAB tools for MLP NNs (e.g., newff, …), design a two-layer feed-forward neural network as a classifier to categorize the input geometric shapes. - The snapshot and bitmap of shapes are given: - Training shapes: shkt.bmp - Training patterns: trn.txt (each shape is in a 125*140 matrix) - Test shapes: shks.bmp - Test patterns: tsn.txt (each shape is in a 125*140 matrix) - Since the dimension of inputs is too high (17500-dimensional), it is not possible to apply them directly to the net. So, … . - Try the number of hidden neurons to be at least. - Do training of NN until all training patterns are truly classified. - To examine the generalization ability of your NN after training, a) Apply it to the test patterns and report the accuracies. b) Add p noise (p=5, 10, …, 75) to the training shapes (only degrade the black pixels of the shapes) and report in a plot the accuracy versus p.
Neural-network-classifier.rar - 神经网络分类器，利用神经网络的学习能力，可以用神经网络实现任意精度的曲线，从而可以将曲线两边的不同对象区别开。

收藏：