Chapter 2 Fundamentals of Machine Learning 

1. 2.1 Various common algorithm illustrations 14

2. 2.2 What is supervised learning, unsupervised learning, semi-supervised learning, and weak supervised learning? 15

3. 2.3 What are the steps insupervised learning? 16

4. 2.4 What is multi-instance learning? 17

5. 2.5 What is the difference between classification networks and regression? 17

6. 2.6 What is a neural network? 17

7. 2.7 Advantages and Disadvantages of Common Classification Algorithms? 18

8. 2.8 Is the correct rate good for evaluating classification algorithms? 20

9. 2.9 How to evaluate a classification algorithm? 20

10. 2.10 What kind of classifier is the best? 22

11. 2.11 The relationship between big data and deep learning 22

12. 2.12 Understanding Local Optimization and Global Optimization 23

13. 2.13 Understanding Logistic Regression 24

14. 2.14 What is the difference between logistic regression and a Naive Bayes Classifier? twenty four

15. 2.15 Why do you need a cost function? 25

16. 2.16 Principle of the function of the cost function 25

17. 2.17 Why is the cost function non-negative? 26

18. 2.18 Common cost function? 26

19. 2.19 Why use cross entropy instead of quadratic cost function? 28

20. 2.20 What is a loss function? 28

21. 2.21 Common loss function 28

22. 2.22 Why does logistic regression use a logarithmic loss function? 30

23. 2.22 How does the logarithmic loss function measure loss? 31

24. 2.23 Why do gradients need to be reduced in machine learning? 32

25. 2.24 What are the disadvantages of the gradient descent method? 32

26. 2.25 Gradient descent method intuitive understanding? 32

27. 2.23 What is the description of the gradient descent algorithm? 33

28. 2.24 How to tune the gradient descent method? 35

29. 2.25 What is the difference between random gradients and batch gradients? 35

30. 2.26 Performance Comparison of Various Gradient Descent Methods 37

31. 2.27 How to calculate the derivative calculation diagram of a graph? 37

32. 2.28 Summary of thoughts on Linear Discriminant Analysis (LDA) 39

33. 2.29 Ideas on Graphical LDA Core 39

34. 2.30 What are the principles of the second class LDA algorithm? 40

35. 2.30 LDA algorithm flow summary 41

36. 2.31 What is the difference between LDA and PCA? 41

37. 2.32 LDA advantages and disadvantages 41

38. 2.33 Summary of thoughts on Principal Component Analysis (PCA) 42

39. 2.34 Graphical PCA Core Ideas 42

40. 2.35 PCA algorithm reasoning 43

41. 2.36 Summary of PCA Algorithm Flow 44

42. 2.37 Main advantages and disadvantages of PCA algorithm 45

43. 2.38 Necessity and purpose of dimensionality reduction 45

44. 2.39 What is the difference between KPCA and PCA? 46

45. 2.40 Model Evaluation 47

46. 2.40.1 Common methods for model evaluation? 47

47. 2.40.2 Empirical error and generalization error 47

48. 2.40.3 Graphic under-fitting, over-fitting 48

49. 2.40.4 How to solve over-fitting and under-fitting? 49

50. 2.40.5 The main role of cross-validation? 50

51. 2.40.6 k fold cross validation? 50

52. 2.40.7 Confusion Matrix 50

53. 2.40.8 Error Rate and Accuracy 51

54. 2.40.9 Precision and recall rate 51

55. 2.40.10 ROC and AUC 52

56. 2.40.11 How to draw ROC curve? 53

57. 2.40.12 How to calculate TPR, FPR? 54

58. 2.40.13 How to calculate Auc? 56

59. 2.40.14 Why use Roc and Auc to evaluate the classifier? 56

60. 2.40.15 Intuitive understanding of AUC 56

61. 2.40.16 Cost-sensitive error rate and cost curve 57

62. 2.40.17 What are the comparison test methods for the model 59

63. 2.40.18 Deviation and variance 59

64. 2.40.19 Why use standard deviation? 60

65. 2.40.20 Point Estimation Thoughts 61

66. 2.40.21 Point Estimation Goodness Principle 61

67. 2.40.22 The connection between point estimation, interval estimation, and central limit theorem? 62

68. 2.40.23 What causes the category imbalance? 62

69. 2.40.24 Common Category Unbalance Problem Resolution 62

70. 2.41 Decision Tree 64

71. 2.41.1 Basic Principles of Decision Trees 64

72. 2.41.2 Three elements of the decision tree? 64

73. 2.41.3 Decision Tree Learning Basic Algorithm 65

74. 2.41.4 Advantages and Disadvantages of Decision Tree Algorithms 65

75. 2.40.5 Concept of entropy and understanding 66

76. 2.40.6 Understanding of Information Gain 66

77. 2.40.7 The role and strategy of pruning treatment? 67

78. 2.41 Support Vector Machine 67

79. 2.41.1 What is a support vector machine 67

80. 2.25.2 What problems are solved by the support vector machine? 68

81. 2.25.2 What doesthe kernel function do? 69

82. 2.25.3 What is the Dual Problem? 69

83. 2.25.4 Understanding Support Vector Regression 69

84. 2.25.5 Understanding SVM (Nuclear Function) 69

85. 2.25.6 What are common kernel functions? 69

86. 2.25.6 Soft Interval and Regularization 73

87. 2.25.7 Main features and disadvantages of SVM 73

88. 2.26 Bayesian 74

89. 2.26.1 Graphical Maximum Likelihood Estimate 74

90. 2.26.2 What is the difference between a naive Bayes classifier and a general Bayesian classifier? 76

91. 2.26.4 Plain and semi-simple Bayesian classifiers 76

92. 2.26.5 Three typical structures of Bayesian network 76

93. 2.26.6 What is the Bayesian error rate 76

94. 2.26.7 What is the Bayesian optimal error rate? 76

95. 2.27 EM algorithm to solve problems and implementation process 76

96. 2.28 Why is there a dimensionality disaster? 78

97. 2.29 How to avoid dimension disasters 82

98. 2.30 What is the difference and connection between clustering and dimension reduction? 82

99. 2.31 Differences between GBDT and random forests 83

100. 2.32 Comparison of four clustering methods 84

P