Table of Contents
Preface vii
Short Introduction to the Wolfram Language xi
1 What Is Machine Learning? 1
2 Machine Learning Paradigms 9
Supervised Learning 9
Unsupervised Learning 12
Reinforcement Learning 15
Other Learning Paradigms 17
3 Classification 27
Car vs. Truck 27
Titanic Survival 30
Topic Classification 35
Image Identification 40
Classification Measures 45
From Probabilities to Decisions 52
4 Regression 61
Car Stopping Distances 61
Brain Weights 65
Boston Homes 68
Regression Measures 73
5 How It Works 81
Model 81
Nonparametric Methods 83
Parametric Methods 89
Model Generalization 95
Overfitting and Underfitting 97
Regularization 103
Hyperparameter Optimization 106
Why Predictions Are Not Perfect 109
6 Clustering 123
Fisher's Irises 123
Face Clustering 127
News Aggregator 130
DNA Hierarchical Clustering 133
7 Dimensionality Reduction 139
Manifold Learning 139
Data Visualization 145
Search 149
Anomaly Detection & Denoising 151
Missing Data Synthesis 153
Autoencoder 154
Recommendation 158
8 Distribution Learning 165
Univariate Data 165
Fisher's Irises 167
Missing Data Synthesis 175
Anomaly Detection 178
9 Data Preprocessing 183
Preprocessing Pipeline 183
Numeric Data 184
Categorical Data 188
Image 191
Text 196
10 Classic Supervised Learning Methods 211
Illustrative Examples 211
Linear Regression 213
Logistic Regression 217
Nearest Neighbors 222
Decision Tree 227
Random Forest 231
Gradient Boosted Trees 236
Support-Vector Machine 242
Gaussian Process 247
Markov Model 259
11 Deep Learning Methods 271
From Neurons to Networks 271
How Neural Networks Learn 281
Convolutional Networks 302
Recurrent Networks 324
Transformer Networks 348
12 Bayesian Inference 379
Coin Flip Experiment 379
Bayesian Inference 382
Bayesian Learning for Predictive Modeling 385
Probabilistic Programming 395
Going Further 401
Index 403
