搜索资源列表
LibSVM
- libsvm的demo的源码实现,通过训练集训练模型,用模型去预测-libsvm source implementation of the demo, through training set model, using the model to predict
BPNN
- 这个程序如何转化成训练BP神经网络连接权值的源代码,提供4组15输入4输出训练集和目标集,调整输出层加权系数.-How this program into training BP neural network connection weights of the source code, provides 4 inputs 4 outputs 15 training set and the target set, adjust the output layer weighting coeffici
lssvm_regression
- 最小二乘支持向量回归模型 直接输入训练集和测试样本即可-Least squares support vector regression model direct input training set and test samples
ID3
- ID3算法(MATLAB平台),包含训练集-ID3 algorithm developed by MATLAB containing the training set
UserCF
- 用C++实现的基于用户的协同过滤算法,包含训练集、测试集-Achieved with C++ user-based collaborative filtering algorithms, including training set, test set
DecisionTree
- 该资源是决策树算法。从“样本特征说明”读取属性,从“样本数据”读取各属性值。 依次取20 —80 (每次递增10 )的样本作为训练集,剩余样本作为测试集测试。-This resource is about decision tree algorithm. The attributes and values can be read by the code from the two txt files. Each time choose a portion of all the data (20
gmm3
- 使用GMM算法对文本特征进行分类,内涵训练集与测试集可以直接使用-Using the GMM algorithm to classify text features, content training set and test set can be used directly
KNN_2011211651
- 应用KNN算法解决0到9的手写数字识别问题,效果在90 以上,内部有两个数据集,一个为训练集(7291个数据),一个为测试数据(2791个数据),程序采用MATLAB编写,另附有文档,程序简洁易懂-Application KNN algorithm to solve 0-9 handwritten digit recognition problem, the effect is more than 90 , the inside has two data sets, one for the tr
pattern_recognition
- 根据训练集图像,对目标图像中的八个子目标图像进行识别,用红色矩形将各个子目标图像框起来,并在子目标图像的中央位置,写上对其识别的结果,即子目标图像的名字。-请键入文字或网站地址,或者上传文档。 取消 Gēnjù xùnliàn jí túxiàng, duì mùbiāo túxiàng zhōng de bā gè zǐ mùbiāo túxiàng jìnxíng shìbié, yòng hóngsè jǔxíng jiāng gège zǐ mùbiāo túxiàng kuān
adaboost
- Adaboost是一种迭代算法,其核心思想是针对同一个训练集训练不同的分类器(弱分类器),然后把这些弱分类器集合起来,构成一个更强的最终分类器(强分类器)。 load clouds [test_targets, E] = lijsada_boost(patterns, targets, patterns, 100, Stumps ,[]) train_patterns 每列为一样本 train_targets 每列为一样本目标 100 :Numbe
bp_demo
- BP神经网络软件(BPGUI):支持手动输入数据和从外部导入数据两种方式;用户可以自定义训练集和测试集占全部数据的百分比,设定完成后,软件随机产生训练集和测试集;支持归一化和不归一化两种数据预处理方式;用户可以自定义网络的结构参数和训练参数;具有绘图功能,可以对比测试集的真实值与预测值;支持网络及数据的保存;具有菜单选项,用户可以通过菜单执行相应的操作;具有右键功能,用户可以通过右键快速执行相应的操作;-The BP neural network software (BPGUI) : suppo
Desktop
- 给出一段汉语文章,根据训练集,将测试集进行分词。-Based on the maximum probability of Chinese segmentation
panda-face-recognition
- gui界面软件,可计算欧几里得距离识别大熊猫面部,具有大量测试集和训练集样本库-gui interface software to calculate the Euclidean distance identification panda face, with a large test set and the training set of sample library
ObjectDetection_Demo
- 这是一个针对图像跟踪的程序,可以检测人脸图像,而且不需要训练集-This is a program for video, can be very good video into a sequence of frames and preserved
semisup_rankboost
- 一种半监督的rankboost算法实现,有训练集,测试集,可以直接运行。-An rankboost semi-supervised algorithm implementation, there is a training set, the test set can be run directly.
pattern-recognition
- 基于特征向量的人脸识别,有训练集和样本集,通过Adaboost强分类器算法实现,结果精确度达到95 以上,给定一个example,就可以在样本集中识别出对应的人脸。-Face recognition based on feature vectors have the training set and sample set by Adaboost strong classifier algorithm, the results of more than 95 accuracy, given an
Adaboost
- 一位同学对adaboost的java实现。Adaboost是一种迭代算法,其核心思想是针对同一个训练集训练不同的分类器(弱分类器),然后把这些弱分类器集合起来,构成一个更强的最终分类器(强分类器)。-adaboost code
dssTree
- 决策树java工程源码,access数据训练集-Java source tree works, access data training set
PJudgetopic
- 机器学习的方法短信情感分类,喜怒哀惧,43123条短信训练集-SMS emotion machine learning classification methods, joy, anger, sadness and fear, 43123 SMS training set
HMMSeg
- java ,隐马尔科夫的分词算法实现。包含10w条训练集,字典。也可以自己重新添加训练集。-java, hidden Markov segmentation algorithm. 10w of the training set contains dictionary. You can also add your own re-training set.