Description: 内涵PCA降维;SMOTE插值;t-SNE降维等算法的随机森林算法，以及鸢尾花数据集，有利于新手或者工程性实验借鉴~(Connotative PCA dimensionality reduction; SMOTE interpolation; t-SNE dimensionality reduction algorithms such as random forest algorithm, as well as iris data sets, is conducive to novice or engineering experiment reference ~) Platform: |
Size: 885760 |
Author:SaoYear |
Hits:
Description: 此程序为非线性降维典型算法之一－－LLE算法,对想进行高维数据降维研究的朋友们值得一看(This program is one of the typical nonlinear dimensionality reduction algorithms-LLE algorithm. Friends who want to study the dimensionality reduction of high-dimensional data are worth a look.) Platform: |
Size: 8192 |
Author:wyrdgi |
Hits:
Description: 第一次作业_基于分类算法的雷达状态识别
对于本数据集中的雷达状态识别，数据降维前使用朴素贝叶斯、支持向量机、神经网络的分类算法对于识别的准确率无太大影响；数据降维后使用神经网络算法最优，支持向量机算法其次，朴素贝叶斯算法较差。此外，训练样本越多，分类准确率有小幅度提高。(First Operation Radar State Recognition Based on Classification Algorithms For radar state recognition in this data set, the classification algorithm of Naive Bayesian, Support Vector Machine and Neural Network before data dimension reduction has little effect on the accuracy of recognition; Neural Network algorithm is the best after data dimension reduction, Support Vector Machine algorithm is the second, Naive Bayesian algorithm is the worst. In addition, the more training samples, the smaller the classification accuracy.) Platform: |
Size: 2841600 |
Author:富察 |
Hits:
Description: KPCA算法属于非线性高维数据集降维，算法其实很简单，数据在低维度空间不是线性可分的，但是在高维度空间就可以变成线性可分的了(The KPCA algorithm belongs to the nonlinear high-dimensional data set dimension reduction. The algorithm is very simple. The data is not linearly separable in the low-dimensional space, but can be linearly separable in the high-dimensional space.) Platform: |
Size: 60416 |
Author:小轩5837 |
Hits:
Description: 基于python，利用主成分分析（PCA）和K近邻算法（KNN）在MNIST手写数据集上进行了分类。
经过PCA降维，最终的KNN在100维的特征空间实现了超过97%的分类精度。(Based on python, it uses principal component analysis (PCA) and K nearest neighbor algorithm (KNN) to classify on the MNIST handwritten data set.
After PCA dimensionality reduction, the final KNN achieved a classification accuracy of over 97% in a 100-dimensional feature space.) Platform: |
Size: 11599872 |
Author:曲小刀 |
Hits:
Search - data reduction algorithm