Beginning Anomaly Detection Using Python-Based Deep Learning. 2 Ed

Table of Contents....5

About the Authors....24

About the Technical Reviewers....25

Acknowledgments....27

Introduction....27

Chapter 1: Introduction to Anomaly Detection....30

What Is an Anomaly?....30

Anomalous Swans....30

Anomalies as Data Points....34

Anomalies in a Time Series....37

Personal Spending Pattern....38

Taxi Cabs....41

Categories of Anomalies....44

Data Point–Based Anomalies....44

Context-Based Anomalies....45

Pattern-Based Anomalies....47

Anomaly Detection....47

Outlier Detection....49

Noise Removal....49

Novelty Detection....50

Event Detection....50

Change Point Detection....50

Anomaly Score Calculation....52

The Three Styles of Anomaly Detection....52

Where Is Anomaly Detection Used?....53

Data Breaches....53

Identity Theft....55

Manufacturing....57

Networking....59

Medicine....59

Video Surveillance....60

Environment....60

Summary....60

Chapter 2: Introduction to Data Science....62

Data Science....63

Dataset....63

Pandas, Scikit-Learn, and Matplotlib....67

Data I/O....68

Data Loading....69

Data Saving....72

DataFrame Creation....72

Data Manipulation....75

Select....75

Filtering....89

Sorting....106

Applying Functions....120

Grouping....130

Combining DataFrames....135

Creating, Renaming, and Dropping Columns....147

Data Analysis....156

Value Counts....156

Pandas .describe() Method....157

Pandas Correlation Matrix....158

Visualization....162

Line Chart....162

Chart Customization....164

Scatter Plot....168

Histogram....169

Bar Graph....169

Data Processing....170

Nulls....171

Categorical Encoding....177

Scaling and Normalizing....186

Feature Engineering and Selection....190

Summary....202

Chapter 3: Introduction to Machine Learning....203

Machine Learning....204

Introduction to Machine Learning....204

Data Splitting....211

Modeling and Evaluation....212

Classification Metrics....217

Regression Metrics....226

Overfitting and Bias-Variance Tradeoff....228

Hyperparameter Tuning....240

Validation....244

Summary....247

Chapter 4: Traditional Machine Learning Algorithms....247

Traditional Machine Learning Algorithms....248

Isolation Forest....248

Example of an Isolation Forest....250

Anomaly Detection with an Isolation Forest....253

Data Preparation....254

Training....261

Hyperparameter Tuning....265

Evaluation and Summary....275

One-Class Support Vector Machine....279

How Does OC-SVM Work?....280

Anomaly Detection with OC-SVM....291

Data Preparation....291

Training....295

Hyperparameter Tuning....300

Evaluation and Summary....303

Summary....307

Chapter 5: Introduction to Deep Learning....308

Introduction to Deep Learning....310

What Is Deep Learning?....310

The Neuron....314

Activation Functions....317

Neural Networks....337

Loss Functions....347

Regression....347

Classification....349

Gradient Descent and Backpropagation....353

Loss Curve....371

Regularization....375

Optimizers....376

Multilayer Perceptron Supervised Anomaly Detection....390

Simple Neural Network: Keras....397

Simple Neural Network: PyTorch....408

Summary....418

Chapter 6: Autoencoders....418

What Are Autoencoders?....419

Simple Autoencoders....422

Sparse Autoencoders....444

Deep Autoencoders....448

Convolutional Autoencoders....450

Denoising Autoencoders....459

Variational Autoencoders....470

Summary....490

Chapter 7: Generative Adversarial Networks....491

What Is a Generative Adversarial Network?....492

Generative Adversarial Network Architecture....496

Wasserstein GAN....499

WGAN-GP....502

Anomaly Detection with a GAN....504

Summary....520

Chapter 8: Long Short-Term Memory Models....520

Sequences and Time Series Analysis....522

What Is an RNN?....525

What Is an LSTM?....526

LSTM for Anomaly Detection....534

Examples of Time Series....563

art_daily_no_noise.csv....564

art_daily_nojump.csv....565

art_daily_jumpsdown.csv....567

art_daily_perfect_square_wave.csv....570

art_load_balancer_spikes.csv....572

ambient_temperature_system_failure.csv....574

ec2_cpu_utilization.csv....576

rds_cpu_utilization.csv....577

Summary....579

Chapter 9: Temporal Convolutional Networks....579

What Is a Temporal Convolutional Network?....580

Dilated Temporal Convolutional Network....587

Anomaly Detection with the Dilated TCN....593

Encoder-Decoder Temporal Convolutional Network....615

Anomaly Detection with the ED-TCN....619

Summary....640

Chapter 10: Transformers....641

What Is a Transformer?....641

Transformer Architecture....646

Transformer Encoder....647

Transformer Decoder....655

Transformer Inference....658

Anomaly Detection with the Transformer....658

Summary....689

Chapter 11: Practical Use Cases and Future Trends of Anomaly Detection....689

Anomaly Detection....690

Real-World Use Cases of Anomaly Detection....694

Telecom....694

Banking....697

Environmental....699

Health Care....702

Transportation....707

Social Media....708

Finance and Insurance....710

Cybersecurity....711

Video Surveillance....716

Manufacturing....718

Smart Home....721

Retail....722

Implementation of Deep Learning–Based Anomaly Detection....722

Future Trends....725

Summary....727

Index....729

Beginning Anomaly Detection Using Python-Based Deep Learning begins with an introduction to anomaly detection, its importance, and its applications. It then covers core data science and machine learning modeling concepts before delving into traditional machine learning algorithms such as OC-SVM and Isolation Forest for anomaly detection using scikit-learn. Following this, the authors explain the essentials of machine learning and deep learning, and how to implement multilayer perceptrons for supervised anomaly detection in both Keras and PyTorch. From here, the focus shifts to the applications of deep learning models for anomaly detection, including various types of autoencoders, recurrent neural networks (via LSTM), temporal convolutional networks, and transformers, with the latter three architectures applied to time-series anomaly detection. This edition has a new chapter on GANs (Generative Adversarial Networks), as well as new material covering  transformer architecture in the context of time-series anomaly detection. 

After completing this book, you will have a thorough understanding of anomaly detection as well as an assortment of methods to approach it in various contexts, including time-series data. Additionally, you will have gained an introduction to scikit-learn, GANs, transformers, Keras, and PyTorch, empowering you to create your own machine learning- or deep learning-based anomaly detectors.

What You Will Learn

• Understand what anomaly detection is, why it it is important, and how it is applied
• Grasp the core concepts of machine learning.
• Master traditional machine learning approaches to anomaly detection using scikit-kearn.
• Understand deep learning in Python using Keras and PyTorch
• Process data through pandas and evaluate your model's performance using metrics like F1-score, precision, and recall
• Apply deep learning to supervised, semi-supervised, and unsupervised anomaly detection tasks for tabular datasets and time series applications

Who This Book Is For

Data scientists and machine learning engineers of all levels of experience interested in learning the basics of deep learning applications in anomaly detection.