NTU-HsuanTienLin-MachineLearning（林轩田机器学习）
1. Course Info
台湾大学林轩田老师曾在coursera上开设了两门机器学习经典课程：《机器学习基石》和《机器学习技法》。这两门课程由浅入深、内容全面，基本涵盖了机器学习领域的很多方面，介绍了机器学习领域经典的一些算法，包括支持向量机、决策树、随机森林、神经网络等等。在此，笔者本人的笔记分享给大家，希望和大家多交流。
首先附上这两门课的主页：
2. 课程内容
2.1 《机器学习基石》
这门课主要涉及机器学习关键问题的四个方面：
-
When Can Machine Learn?
-
Why Can Machine Learn?
-
How Can Machine Learn?
-
How Can Machine Learn Better?
其中每个方面包含4节课，总共有16节课。具体所有课程内容如下：
-
When Can Machine Learn?
-
[The Learning Problem]
-
[Learning to Answer Yes/No]
-
[Types of Learning]
-
[Feasibility of Learning]
-
Why Can Machine Learn?
-
[Training versus Testing]
-
[Theory of Generalization]
-
[The VC Dimension]
-
[Noise and Error]
-
How Can Machine Learn?
-
[Linear Regression]
-
[Logistic Regression]
-
[Linear Models for Classification]
-
[Nonlinear Transformation]
-
How Can Machine Learn Better?
-
[Hazard of Overfitting]
-
[Regularization]
-
[Validation]
-
[Three Learning Principles]
2.2 《机器学习技法》
这门课主要涉及机器学习经典算法的三个方面：
-
Embedding Numerous Features: Kernel Models
-
Combining Predictive Features: Aggregation Models
-
Distilling Implicit Features: Extraction Models
总共有16节课。具体所有课程内容如下：
-
Embedding Numerous Features: Kernel Models
-
[Linear Support Vector Machine]
-
[Dual Support Vector Machine]
-
[Kernel Support Vector Machine]
-
[Soft-Margin Support Vector Machine]
-
[Kernel Logistic Regression]
-
[Support Vector Regression]
-
Combining Predictive Features: Aggregation Models
-
[Blending and Bagging]
-
[Adaptive Boosting]
-
[Decision Tree]
-
[Random Forest]
-
[Gradient Boosted Decision Tree]
-
Distilling Implicit Features: Extraction Models
-
[Neural Network]
- [Deep Learning]
-
[Radial Basis Function Network]
-
[Matrix Factorization]
- [Finale]
3. 资源汇总
笔者在学习这门课的过程中整理了各种课程资源，包括视频、笔记、书籍等。具体如下：
3.1 课程视频
Youtube上的课程视频在如下：
3.2 课程课件
此项目包含了林轩田机器学习课程完整的课件PPT
3.3 课程笔记
这是笔者最用心整理也是花的时间最多的，读者可以边看视频边看我的笔记，希望能给读者提供微薄之力。
3.4 参考书籍
林轩田机器学习基石这门课有一个配套教材：《Learning From Data》，林轩田也是编者之一。这本书的主页为：