台湾大学 机器学习基石(Machine Learning Foundation) 林轩田老师

admin

台湾大学 机器学习基石(Machine Learning Foundation) 林轩田老师 中文讲课+课件


台湾大学机器学习基石ntumlone-002

云计算说到底最核心的还是数据分析和机器学习

这哥们讲得很好，其个人水平很高，讲解得也很清楚，Coursera难得的中文授课课程，看录屏就不用花几个月去上课

看不懂《机器学习技法》的同学 先看这个课程

【课程内容】


When Can Machines Learn? [何时可以使用机器学习]
The Learning Problem [机器学习问题]
Learning to Answer Yes/No [二元分类]
Types of Learning [各式机器学习问题]
Feasibility of Learning [机器学习的可行性]
Why Can Machines Learn? [为什麽机器可以学习]
Training versus Testing [训练与测试]
Theory of Generalization [举一反三的一般化理论]
The VC Dimension [VC 维度]
Noise and Error [杂讯时错误]
How Can Machines Learn? [机器可以怎麽样学习]
Linear Regression [线性迴归]
Linear `Soft" Classification [软性的线性分类]
Linear Classification beyond Yes/No [二元分类以外的分类问题]
Nonlinear Transformation [非线性转换]
How Can Machines Learn Better? [机器可以怎麽样学得更好]
Hazard of Overfitting [过度训练的危险]
Preventing Overfitting I: Regularization [避免过度训练一：控制调适]
Preventing Overfitting II: Validation [避免过度训练二：自我检测]
Three Learning Principles [三个机器学习的重要原则]

│  
├─视频
│      1 - 1 - Course Introduction (10_58).avi
│      1 - 2 - What is Machine Learning (18_28).avi
│      1 - 3 - Applications of Machine Learning (18_56).avi
│      1 - 4 - Components of Machine Learning (11_45).avi
│      1 - 5 - Machine Learning and Other Fields (10_21).avi
│      2 - 1 - Perceptron Hypothesis Set (15_42).avi
│      2 - 2 - Perceptron Learning Algorithm (PLA) (19_46).avi
│      2 - 3 - Guarantee of PLA (12_37).avi
│      2 - 4 - Non-Separable Data (12_55).avi
│      3 - 1 - Learning with Different Output Space (17_26).avi
│      3 - 2 - Learning with Different Data Label (18_12).avi
│      3 - 3 - Learning with Different Protocol (11_09).avi
│      3 - 4 - Learning with Different Input Space (14_13).avi
│      4 - 1 - Learning is Impossible_ (13_32).avi
│      4 - 2 - Probability to the Rescue (11_33).avi
│      4 - 3 - Connection to Learning (16_46).avi
│      4 - 4 - Connection to Real Learning (18_06).avi
│      5 - 1 - Recap and Preview (13_44).avi
│      5 - 2 - Effective Number of Lines (15_26).avi
│      5 - 3 - Effective Number of Hypotheses (16_17).avi
│      5 - 4 - Break Point (07_44).avi
│      6 - 1 - Restriction of Break Point (14_18).avi
│      6 - 2 - Bounding Function_ Basic Cases (06_56).avi
│      6 - 3 - Bounding Function_ Inductive Cases (14_47).avi
│      6 - 4 - A Pictorial Proof (16_01).avi
│      7 - 1 - Definition of VC Dimension (13_10).avi
│      7 - 2 - VC Dimension of Perceptrons (13_27).avi
│      7 - 3 - Physical Intuition of VC Dimension (6_11).avi
│      7 - 4 - Interpreting VC Dimension (17_13).avi
│      8 - 1 - Noise and Probabilistic Target (17_01).avi
│      8 - 2 - Error Measure (15_10).avi
│      8 - 3 - Algorithmic Error Measure (13_46).avi
│      8 - 4 - Weighted Classification (16_54).avi
│      9 - 1 - Linear Regression Problem (10_08).avi
│      9 - 2 - Linear Regression Algorithm (20_03).avi
│      9 - 3 - Generalization Issue (20_34).avi
│      9 - 4 - Linear Regression for Binary Classification (11_23).avi
│      10 - 1 - Logistic Regression Problem (14_33).avi
│      10 - 2 - Logistic Regression Error (15_58).avi
│      10 - 3 - Gradient of Logistic Regression Error (15_38).avi
│      10 - 4 - Gradient Descent (19_18).avi
│      11 - 1 - Linear Models for Binary Classification (21_35).avi
│      11 - 2 - Stochastic Gradient Descent (11_39).avi
│      11 - 3 - Multiclass via Logistic Regression (14_18).avi
│      11 - 4 - Multiclass via Binary Classification (11_35).avi
│      12 - 1 - Quadratic Hypothesis (23_47).avi
│      12 - 2 - Nonlinear Transform (09_52).avi
│      12 - 3 - Price of Nonlinear Transform (15_37).avi
│      12 - 4 - Structured Hypothesis Sets (09_36).avi
│      13 - 1 - What is Overfitting_ (10_45).avi
│      13 - 2 - The Role of Noise and Data Size (13_36).avi
│      13 - 3 - Deterministic Noise (14_07).avi
│      13 - 4 - Dealing with Overfitting (10_49).avi
│      14 - 1 - Regularized Hypothesis Set (19_16).avi
│      14 - 2 - Weight Decay Regularization (24_08).avi
│      14 - 3 - Regularization and VC Theory (08_15).avi
│      14 - 4 - General Regularizers (13_28).avi
│      15 - 1 - Model Selection Problem (16_00).avi
│      15 - 2 - Validation (13_24).avi
│      15 - 3 - Leave-One-Out Cross Validation (16_06).avi
│      15 - 4 - V-Fold Cross Validation (10_41).avi
│      16 - 1 - Occam_'s Razor (10_08).avi
│      16 - 2 - Sampling Bias (11_50).avi
│      16 - 3 - Data Snooping (12_28).avi
│      16 - 4 - Power of Three (08_49).avi
│      
└─资料
下载地址

游客，如果您要查看本帖隐藏内容请回复

uliz2011

Thanks for sharing