GV

GeezerVison

The World Wide Web, restored to 800 pixels of glory.

Home|About|Gaming cabinet|Archives|How it works|Starter sites

On this site

  • Sign in
  • ActionsCI/CD and automation
  • CodespacesCloud development environments
  • All Features
  • Documentation
  • Training
  • Certifications
  • Build with Copilot
  • Customize Copilot
  • Integrations
  • Trending repos
  • GitHub Sponsors
  • Developer articles
  • Enterprises

This view

  • Original page
  • New address

GeezerVison is showing github.com — GitHub - LebranceBW/MLcode: 《机器学习》一书中涉及到的代码(python)

BranchesTags
Open more actions menu

Latest commit

 

History

60 Commits
60 Commits

Folders and files

NameName
Last commit message
Last commit date
.vscode
.vscode
 
 
BayesModel
BayesModel
 
 
DecisionTree
DecisionTree
 
 
EnsembleLearning
EnsembleLearning
 
 
Img
Img
 
 
KNearestNeighbor
KNearestNeighbor
 
 
LinerModel
LinerModel
 
 
NeuralNet
NeuralNet
 
 
SVM
SVM
 
 
dataSet
dataSet
 
 
lib
lib
 
 
.gitignore
.gitignore
 
 
BPNN.log
BPNN.log
 
 
readme.md
readme.md
 
 

Repository files navigation

《机器学习》一书中涉及到的代码

1.线性模型

1.1对数几率回归 📎

原题在西瓜书P69页3.3

LogisticRe

2.决策树 📎

完成了两种评价方式与三种剪枝策略的离散决策树的编写,评价函数对决策树的影响有限。PS:连续值的决策树与多变量决策树有点难,脑壳疼不想写😋

DT

3.神经网络

3.1.累积形BP神经网络 📎

针对书上的西瓜数据集3.0,用BP神经网络进行了拟合,最好结果为: 学习率为0.05,隐含层维度为8,最终测试集误差为0.12090,训练了4330次,正确率为:1.00000 ps:我就是传说中的调参工程师

BP

3.2.RBF神经网络 📎

用RBF网络实现了异或操作,中间层4阶,学习率0.1,迭代1k次结果为:

  • 0 xor 0 is 0.025424
  • 0 xor 1 is 0.938498
  • 1 xor 0 is 0.868398
  • 1 xor 1 is 0.163135

4.支持向量机(SVM)

4.1 线性核与高斯核SVM在西瓜3.0α上的分类结果 📎

准确率明显高斯核('-s 0 -t 2 -c 1000')比线性核('-s 0 -t 0 -c 100')高

SVM

5.集成学习

5.1 AdaBoost 📎

使用AdaBoost对决策树桩进行提升生成分类器。在西瓜3.0α训练集上的效果(8轮)如图

AdaBoost

6.K近邻算法 📎

采用KD树检索样本点

KNN

About

《机器学习》一书中涉及到的代码(python)

Topics

machine-learning

Resources

Readme
Activity

Stars

6 stars

Watchers

1 watching

Forks

1 fork
Report repository

Releases

Packages

Contributors

Languages

You are visitor 01402503 — GeezerVison does not store the pages you look up.
Best viewed with Netscape Navigator 4.7 or Internet Explorer 6 at 800×600. No cookies required.