---
type: CKG Bundle
title: Machine Learning Textbook
tags: [CS & AI]
timestamp: 2026-06-18T00:00:00Z
ckg:
  id: machine-learning-textbook
  nodes: 200
  license: CC BY 4.0
---

# Machine Learning Textbook — Compressed Knowledge Graph

```csv
ConceptID,ConceptLabel,TaxonomyID
1,Machine Learning,FOUND
2,Supervised Learning,FOUND
3,Unsupervised Learning,FOUND
4,Classification,FOUND
5,Regression,FOUND
6,Training Data,FOUND
7,Test Data,FOUND
8,Validation Data,FOUND
9,Feature,FOUND
10,Label,FOUND
11,Instance,FOUND
12,Feature Vector,FOUND
13,Model,FOUND
14,Algorithm,FOUND
15,Hyperparameter,FOUND
16,K-Nearest Neighbors,KNN
17,Distance Metric,KNN
18,Euclidean Distance,KNN
19,Manhattan Distance,KNN
20,K Selection,KNN
21,Decision Boundary,KNN
22,Voronoi Diagram,KNN
23,Curse of Dimensionality,KNN
24,KNN for Classification,KNN
25,KNN for Regression,KNN
26,Lazy Learning,KNN
27,Decision Tree,TREE
28,Tree Node,TREE
29,Leaf Node,TREE
30,Splitting Criterion,TREE
31,Entropy,TREE
32,Information Gain,TREE
33,Gini Impurity,TREE
34,Pruning,TREE
35,Overfitting,TREE
36,Underfitting,TREE
37,Tree Depth,TREE
38,Categorical Features,FOUND
39,Continuous Features,FOUND
40,Feature Space Partitioning,FOUND
41,Logistic Regression,MISC
42,Sigmoid Function,LOGREG
43,Log-Loss,LOGREG
44,Binary Classification,LOGREG
45,Multiclass Classification,LOGREG
46,Maximum Likelihood,LOGREG
47,One-vs-All,LOGREG
48,One-vs-One,LOGREG
49,Softmax Function,LOGREG
50,Regularization,REG
51,L1 Regularization,REG
52,L2 Regularization,REG
53,Ridge Regression,REG
54,Lasso Regression,REG
55,Support Vector Machine,SVM
56,Hyperplane,SVM
57,Margin,SVM
58,Support Vectors,SVM
59,Margin Maximization,SVM
60,Hard Margin SVM,SVM
61,Soft Margin SVM,SVM
62,Slack Variables,SVM
63,Kernel Trick,SVM
64,Linear Kernel,SVM
65,Polynomial Kernel,SVM
66,Radial Basis Function,SVM
67,Gaussian Kernel,SVM
68,Dual Formulation,SVM
69,Primal Formulation,SVM
70,K-Means Clustering,CLUST
71,Centroid,CLUST
72,Cluster Assignment,CLUST
73,Cluster Update,CLUST
74,K-Means Initialization,CLUST
75,Random Initialization,CLUST
76,K-Means++ Initialization,CLUST
77,Elbow Method,CLUST
78,Silhouette Score,CLUST
79,Within-Cluster Variance,CLUST
80,Convergence Criteria,CLUST
81,Inertia,CLUST
82,Neural Network,NN
83,Artificial Neuron,NN
84,Perceptron,NN
85,Activation Function,NN
86,ReLU,NN
87,Tanh,NN
88,Sigmoid Activation,LOGREG
89,Leaky ReLU,NN
90,Weights,NN
91,Bias,NN
92,Forward Propagation,NN
93,Backpropagation,NN
94,Gradient Descent,NN
95,Stochastic Gradient Descent,NN
96,Mini-Batch Gradient Descent,NN
97,Learning Rate,NN
98,Loss Function,NN
99,Mean Squared Error,NN
100,Cross-Entropy Loss,TREE
101,Epoch,NN
102,Batch Size,NN
103,Vanishing Gradient,NN
104,Exploding Gradient,NN
105,Weight Initialization,NN
106,Xavier Initialization,NN
107,He Initialization,NN
108,Fully Connected Layer,NN
109,Hidden Layer,NN
110,Output Layer,NN
111,Input Layer,NN
112,Network Architecture,NN
113,Deep Learning,NN
114,Multilayer Perceptron,NN
115,Universal Approximation,NN
116,Convolutional Neural Network,CNN
117,Convolution Operation,CNN
118,Filter,CNN
119,Kernel Size,SVM
120,Stride,CNN
121,Padding,CNN
122,Valid Padding,CNN
123,Same Padding,CNN
124,Feature Map,FOUND
125,Receptive Field,CNN
126,Pooling Layer,NN
127,Max Pooling,CNN
128,Average Pooling,CNN
129,Spatial Hierarchies,CNN
130,Translation Invariance,CNN
131,Local Connectivity,CNN
132,Weight Sharing,CNN
133,CNN Architecture,CNN
134,LeNet,CNN
135,AlexNet,CNN
136,VGG,CNN
137,ResNet,CNN
138,Inception,CNN
139,Transfer Learning,TL
140,Pre-Trained Model,FOUND
141,Fine-Tuning,TL
142,Feature Extraction,FOUND
143,Domain Adaptation,TL
144,ImageNet,TL
145,Model Zoo,FOUND
146,Freezing Layers,NN
147,Learning Rate Scheduling,NN
148,Bias-Variance Tradeoff,NN
149,Training Error,EVAL
150,Validation Error,FOUND
151,Test Error,EVAL
152,Generalization,EVAL
153,Cross-Validation,FOUND
154,K-Fold Cross-Validation,FOUND
155,Stratified Sampling,EVAL
156,Holdout Method,EVAL
157,Confusion Matrix,EVAL
158,True Positive,EVAL
159,False Positive,EVAL
160,True Negative,EVAL
161,False Negative,EVAL
162,Accuracy,EVAL
163,Precision,EVAL
164,Recall,EVAL
165,F1 Score,EVAL
166,ROC Curve,EVAL
167,AUC,EVAL
168,Sensitivity,EVAL
169,Specificity,EVAL
170,Data Preprocessing,EVAL
171,Normalization,PREP
172,Standardization,PREP
173,Min-Max Scaling,PREP
174,Z-Score Normalization,PREP
175,One-Hot Encoding,PREP
176,Label Encoding,FOUND
177,Feature Engineering,FOUND
178,Feature Selection,FOUND
179,Dimensionality Reduction,PREP
180,Data Augmentation,PREP
181,Computational Complexity,OPT
182,Time Complexity,OPT
183,Space Complexity,OPT
184,Scalability,OPT
185,Batch Processing,NN
186,Online Learning,OPT
187,Optimizer,OPT
188,Adam Optimizer,OPT
189,RMSprop,OPT
190,Momentum,OPT
191,Nesterov Momentum,OPT
192,Gradient Clipping,OPT
193,Dropout,OPT
194,Early Stopping,OPT
195,Model Evaluation,FOUND
196,Model Selection,FOUND
197,Hyperparameter Tuning,FOUND
198,Grid Search,OPT
199,Random Search,OPT
200,Bayesian Optimization,OPT
```

## Edges (prerequisite -> concept)
1 -> 2
1 -> 3
2 -> 4
2 -> 5
1 -> 6
6 -> 7
6 -> 8
1 -> 9
2 -> 10
9 -> 11
9 -> 12
11 -> 12
1 -> 13
1 -> 14
13 -> 15
14 -> 15
2 -> 16
14 -> 16
9 -> 17
17 -> 18
17 -> 19
15 -> 20
16 -> 20
4 -> 21
16 -> 22
21 -> 22
9 -> 23
17 -> 23
16 -> 24
4 -> 24
16 -> 25
5 -> 25
16 -> 26
2 -> 27
14 -> 27
27 -> 28
27 -> 29
28 -> 29
27 -> 30
30 -> 31
31 -> 32
30 -> 33
27 -> 34
35 -> 34
13 -> 35
6 -> 35
13 -> 36
6 -> 36
27 -> 37
28 -> 37
9 -> 38
9 -> 39
27 -> 40
9 -> 40
2 -> 41
14 -> 41
4 -> 41
41 -> 42
98 -> 43
41 -> 43
4 -> 44
4 -> 45
41 -> 46
45 -> 47
41 -> 47
45 -> 48
41 -> 48
45 -> 49
35 -> 50
50 -> 51
50 -> 52
52 -> 53
5 -> 53
51 -> 54
5 -> 54
2 -> 55
14 -> 55
4 -> 55
55 -> 56
55 -> 57
56 -> 57
55 -> 58
57 -> 58
57 -> 59
55 -> 60
57 -> 60
55 -> 61
57 -> 61
61 -> 62
55 -> 63
63 -> 64
63 -> 65
63 -> 66
63 -> 67
66 -> 67
55 -> 68
55 -> 69
3 -> 70
14 -> 70
70 -> 71
70 -> 72
71 -> 72
70 -> 73
71 -> 73
70 -> 74
74 -> 75
74 -> 76
70 -> 77
15 -> 77
70 -> 78
70 -> 79
71 -> 79
70 -> 80
70 -> 81
79 -> 81
2 -> 82
14 -> 82
82 -> 83
83 -> 84
83 -> 85
85 -> 86
85 -> 87
85 -> 88
85 -> 89
86 -> 89
83 -> 90
83 -> 91
82 -> 92
83 -> 92
82 -> 93
92 -> 93
93 -> 94
94 -> 95
94 -> 96
94 -> 97
15 -> 97
13 -> 98
98 -> 99
5 -> 99
98 -> 100
4 -> 100
6 -> 101
82 -> 101
6 -> 102
82 -> 102
93 -> 103
94 -> 103
93 -> 104
94 -> 104
82 -> 105
90 -> 105
105 -> 106
105 -> 107
82 -> 108
82 -> 109
108 -> 109
82 -> 110
108 -> 110
82 -> 111
108 -> 111
82 -> 112
82 -> 113
82 -> 114
109 -> 114
82 -> 115
113 -> 116
14 -> 116
116 -> 117
117 -> 118
118 -> 119
15 -> 119
117 -> 120
117 -> 121
121 -> 122
121 -> 123
117 -> 124
118 -> 124
116 -> 125
117 -> 125
116 -> 126
126 -> 127
126 -> 128
116 -> 129
124 -> 129
116 -> 130
117 -> 130
116 -> 131
117 -> 131
116 -> 132
90 -> 132
116 -> 133
133 -> 134
133 -> 135
133 -> 136
133 -> 137
133 -> 138
113 -> 139
14 -> 139
139 -> 140
139 -> 141
140 -> 141
139 -> 142
140 -> 142
139 -> 143
116 -> 144
140 -> 144
140 -> 145
141 -> 146
97 -> 147
139 -> 147
35 -> 148
36 -> 148
6 -> 149
13 -> 149
8 -> 150
13 -> 150
7 -> 151
13 -> 151
148 -> 152
149 -> 152
150 -> 152
8 -> 153
13 -> 153
153 -> 154
153 -> 155
6 -> 156
7 -> 156
8 -> 156
4 -> 157
157 -> 158
157 -> 159
157 -> 160
157 -> 161
157 -> 162
158 -> 163
159 -> 163
158 -> 164
161 -> 164
163 -> 165
164 -> 165
4 -> 166
166 -> 167
164 -> 168
160 -> 169
159 -> 169
6 -> 170
170 -> 171
170 -> 172
171 -> 173
172 -> 174
170 -> 175
38 -> 175
170 -> 176
10 -> 176
9 -> 177
170 -> 177
177 -> 178
9 -> 179
23 -> 179
170 -> 180
116 -> 180
14 -> 181
181 -> 182
181 -> 183
181 -> 184
6 -> 185
102 -> 185
1 -> 186
6 -> 186
94 -> 187
187 -> 188
187 -> 189
94 -> 190
187 -> 190
190 -> 191
104 -> 192
50 -> 193
82 -> 193
50 -> 194
150 -> 194
13 -> 195
7 -> 195
13 -> 196
195 -> 196
15 -> 197
196 -> 197
197 -> 198
197 -> 199
197 -> 200

*Free CKG · Graphify.md · `pip install ckg-mcp` for all · own the knowledge layer, rent the model*