plotted for comparison on (a) a n...Figure 4.6 In both of these plots the correlation between x and y will be cl...Figure 4.7 This dataset will have ordinal correlation of 1, since y consiste...Figure 4.8 Residuals measure the accuracy of a model. Here the gray points a...Figure 4.9 A degenerative form of “curve fitting” is used as a base of compa...Figure 4.10 Large residuals can come from two sources: either that data we a...Figure 4.11 The most intuitive way to think of a probability distribution is...Figure 4.12 The area under the curve of a continuous probability is distribu...Figure 4.13 The Bernoulli distribution is just the flipping of a biased coin...Figure 4.14 The uniform distribution gives constantly probability density ov...Figure 4.15 The normal distribution, aka Gaussian, is the prototypical “bell...Figure 4.16 The exponential distribution is often used to estimate the lengt...Figure 4.17 Say there are many independent events that could happen (there a...3 Chapter 5Figure 5.1 K‐fold cross‐validation breaks the dataset into k partitions. Eac...Figure 5.2 The performance of a classifier can't really be boiled down to a ...Figure 5.3 The ROC curve plots the true/false positive rate for a classifier...Figure 5.4 For this cutoff the fraction of all 0s that get incorrectly flagg...Figure 5.5 For this cutoff a small change in your classification threshold w...Figure 5.6 In a lift curve the x‐axis (the “reach”) is the fraction of all d...Figure 5.7 A decision tree classifier is somewhat like a flow chart. Every n...Figure 5.8 Support vector machines look for a hyperplane that divides your t...Figure 5.9 The key weakness of support vector machines is that often there i...Figure 5.10 Sometimes you can fix the linear separability problem by mapping...Figure 5.11 The Sigmoid function shows up many places in machine learning. E...Figure 5.12 A perceptron is a neural network with a single hidden layer.Figure 5.13 The “curse of dimensionality” describes how high‐dimensional spa...Figure 5.14 If many fields in your data move in lock‐step then in a sense th...Figure 5.15 A Scree plot shows how much of a dataset's variability is accoun...Figure 5.16 The “clusters” identified by k‐means clustering are really just ...Figure 5.17 The indicated point is closer to the middle of the other cluster...
4 Chapter 6Figure 6.1 The map‐reduce paradigm is one of the building blocks of the Big ...
5 Chapter 7Figure 7.1 A neural network consists of “nodes” arranged into “layers.” Each...Figure 7.2 Convolutional neural networks are stars in image processing. The ...
Guide
7 Index
8 WILEY END USER LICENSE AGREEMENT
Pages
1 iv
2 v
3 1
4 2
5 3
6 4
7 5
8 7
9 8
10 9
11 10
12 11
13 12
14 13
15 14
16 15
17 16
18 17
19 18
20 19
21 20
22 21
23 22
24 23
25 24
26 25
27 26
28 27
29 28
30 29
