Table 1.1 | The Contact Lens Data | 7 |
Table 1.2 | The Weather Data | 11 |
Table 1.3 | Weather Data With Some Numeric Attributes | 12 |
Table 1.4 | The Iris Data | 15 |
Table 1.5 | The CPU Performance Data | 16 |
Table 1.6 | The Labor Negotiations Data | 17 |
Table 1.7 | The Soybean Data | 20 |
Table 2.1 | Iris Data as a Clustering Problem | 46 |
Table 2.2 | Weather Data With a Numeric Class | 47 |
Table 2.3 | Family Tree | 48 |
Table 2.4 | The Sister-of Relation | 49 |
Table 2.5 | Another Relation | 52 |
Table 3.1 | A New Iris Flower | 80 |
Table 3.2 | Training Data for the Shapes Problem | 83 |
Table 4.1 | Evaluating the Attributes in the Weather Data | 94 |
Table 4.2 | The Weather Data, With Counts and Probabilities | 97 |
Table 4.3 | A New Day | 98 |
Table 4.4 | The Numeric Weather Data With Summary Statistics | 101 |
Table 4.5 | Another New Day | 102 |
Table 4.6 | The Weather Data with Identification Codes | 111 |
Table 4.7 | Gain Ratio Calculations for the Tree Stumps of Fig. 4.2 | 112 |
Table 4.8 | Part of the Contact Lens Data for which Astigmatism=Yes | 116 |
Table 4.9 | Part of the Contact Lens Data for Which Astigmatism=Yes and Tear Production Rate=Normal | 117 |
Table 4.10 | Item Sets for the Weather Data With Coverage 2 or Greater | 121 |
Table 4.11 | Association Rules for the Weather Data | 123 |
Table 5.1 | Confidence Limits for the Normal Distribution | 166 |
Table 5.2 | Confidence Limits for Student’s Distribution With 9 Degrees of Freedom | 174 |
Table 5.3 | Different Outcomes of a Two-Class Prediction | 180 |
Table 5.4 | Different Outcomes of a Three-Class Prediction: (A) Actual; (B) Expected | 181 |
Table 5.5 | Default Cost Matrixes: (A) Two-Class Case; (B) Three-Class Case | 182 |
Table 5.6 | Data for a Lift Chart | 184 |
Table 5.7 | Different Measures Used to Evaluate the False Positive Versus False Negative Tradeoff | 191 |
Table 5.8 | Performance Measures for Numeric Prediction | 195 |
Table 5.9 | Performance Measures for Four Numeric Prediction Models | 197 |
Table 6.1 | Preparing the Weather Data for Insertion Into an FP-tree: (A) The Original Data; (B) Frequency Ordering of Items With Frequent Item Sets in Bold; (C) The Data With Each Instance Sorted Into Frequency Order; (D) The Two Multiple-Item Frequent Item Sets | 236 |
Table 7.1 | Linear Models in the Model Tree | 280 |
Table 8.1 | The First Five Instances From the CPU Performance Data; (A) Original Values; (B) The First Partial Least Squares Direction; (C) Residuals From the First Direction | 308 |
Table 8.2 | Transforming a Multiclass Problem Into a Two-Class One: (A) Standard Method; (B) Error-Correcting Code | 324 |
Table 8.3 | A Nested Dichotomy in the Form of a Code Matrix | 327 |
Table 9.1 | Highest Probability Words and User Tags From a Sample of Topics Extracted From a Collection of Scientific Articles | 381 |
Table 9.2 | Link Functions, Mean Functions, and Distributions Used in Generalized Linear Models | 401 |
Table 10.1 | Summary of Performance on the MNIST Evaluation | 421 |
Table 10.2 | Loss Functions, Corresponding Distributions, and Activation Functions | 423 |
Table 10.3 | Activation Functions and Their Derivatives | 425 |
Table 10.4 | Convolutional Neural Network Performance on the ImageNet Challenge | 439 |
Table 10.5 | Components of a “Long Short-Term Memory” Recurrent Neural Network | 459 |
Table 13.1 | The Top 10 Algorithms in Data Mining, According to a 2006 Poll | 504 |
18.226.177.125