Chapter 1 Introduction to AI 3

1.1 What Is AI? 3

1.2 The History of AI 5

1.3 AI Hypes and AI Winters 9

1.4 The Types of AI 11

1.5 Edge AI and Cloud AI 12

1.6 Key Moments of AI 14

1.7 The State of AI 17

1.8 AI Resources 19

1.9 Summary 21

1.10 Chapter Review Questions 22

Chapter 2 AI Development Tools 23

2.1 AI Hardware Tools 23

2.2 AI Software Tools 24

2.3 Introduction to Python 27

2.4 Python Development Environments 30

2.4 Getting Started with Python 34

2.5 AI Datasets 45

2.6 Python AI Frameworks 47

2.7 Summary 49

2.8 Chapter Review Questions 50

Part II Machine Learning and Deep Learning

Chapter 3 Machine Learning 53

3.1 Introduction 53

3.2 Supervised Learning: Classifications 55

Scikit-Learn Datasets 56

Support Vector Machines 56

Naive Bayes 67

Linear Discriminant Analysis 69

Principal Component Analysis 70

Decision Tree 73

Random Forest 76

K-Nearest Neighbors 77

Neural Networks 78

3.3 Supervised Learning: Regressions 80

3.4 Unsupervised Learning 89

K-means Clustering 89

3.5 Semi-supervised Learning 91

3.6 Reinforcement Learning 93

Q-Learning 95

3.7 Ensemble Learning 102

3.8 AutoML 106

3.9 PyCaret 109

3.10 LazyPredict 111

3.11 Summary 115

3.12 Chapter Review Questions 116

Chapter 4 Deep Learning 117

4.1 Introduction 117

4.2 Artificial Neural Networks 120

4.3 Convolutional Neural Networks 125

4.3.1 LeNet, AlexNet, GoogLeNet 129

4.3.2 VGG, ResNet, DenseNet, MobileNet, EffecientNet, and YOLO 140

4.3.3 U-Net 152

4.3.4 AutoEncoder 157

4.3.5 Siamese Neural Networks 161

4.3.6 Capsule Networks 163

4.3.7 CNN Layers Visualization 165

4.4 Recurrent Neural Networks 173

4.4.1 Vanilla RNNs 175

4.4.2 Long-Short Term Memory 176

4.4.3 Natural Language Processing and Python Natural Language Toolkit 183

4.5 Transformers 187

4.5.1 BERT and ALBERT 187

4.5.2 GPT-3 189

4.5.3 Switch Transformers 190

4.6 Graph Neural Networks 191

4.6.1 SuperGLUE 192

4.7 Bayesian Neural Networks 192

4.8 Meta Learning 195

4.9 Summary 197

4.10 Chapter Review Questions 197

Part III AI Applications

Chapter 5 Image Classification 201

5.1 Introduction 201

5.2 Classification with Pre-trained Models 203

5.3 Classification with Custom Trained Models: Transfer Learning 209

5.4 Cancer/Disease Detection 227

5.4.1 Skin Cancer Image Classification 227

5.4.2 Retinopathy Classification 229

5.4.3 Chest X-Ray Classification 230

5.4.5 Brain Tumor MRI Image Classification 231

5.4.5 RSNA Intracranial Hemorrhage Detection 231

5.5 Federated Learning for Image Classification 232

5.6 Web-Based Image Classification 233

5.6.1 Streamlit Image File Classification 234

5.6.2 Streamlit Webcam Image Classification 242

5.6.3 Streamlit from GitHub 248

5.6.4 Streamlit Deployment 249

5.7 Image Processing 250

5.7.1 Image Stitching 250

5.7.2 Image Inpainting 253

5.7.3 Image Coloring 255

5.7.4 Image Super Resolution 256

5.7.5 Gabor Filter 257

5.8 Summary 262

5.9 Chapter Review Questions 263

Chapter 6 Face Detection and Face Recognition 265

6.1 Introduction 265

6.2 Face Detection and Face Landmarks 266

6.3 Face Recognition 279

6.3.1 Face Recognition with Face_Recognition 279

6.3.2 Face Recognition with OpenCV 285

6.3.3 GUI-Based Face Recognition System 288

Other GUI Development Libraries 300

6.3.4 Google FaceNet 301

6.4 Age, Gender, and Emotion Detection 301

6.4.1 DeepFace 302

6.4.2 TCS-HumAIn-2019 305

6.5 Face Swap 309

6.5.1 Face_Recognition and OpenCV 310

6.5.2 Simple_Faceswap 315

6.5.3 DeepFaceLab 322

6.6 Face Detection Web Apps 322

6.7 How to Defeat Face Recognition 334

6.8 Summary 335

6.9 Chapter Review Questions 336

Chapter 7 Object Detections and Image Segmentations 337

7.1 Introduction 337

R-CNN Family 338

YOLO 339

SSD 340

7.2 Object Detections with Pretrained Models 341

7.2.1 Object Detection with OpenCV 341

7.2.2 Object Detection with YOLO 346

7.2.3 Object Detection with OpenCV and Deep Learning 351

7.2.4 Object Detection with TensorFlow, ImageAI, Mask RNN, PixelLib, Gluon 354

TensorFlow Object Detection 354

ImageAI Object Detection 355

MaskRCNN Object Detection 357

Gluon Object Detection 363

7.2.5 Object Detection with Colab OpenCV 364

7.3 Object Detections with Custom Trained Models 369

7.3.1 OpenCV 369

Step 1 369

Step 2 369

Step 3 369

Step 4 370

Step 5 371

7.3.2 YOLO 372

Step 1 372

Step 2 372

Step 3 373

Step 4 375

Step 5 375

7.3.3 TensorFlow, Gluon, and ImageAI 376

TensorFlow 376

Gluon 376

ImageAI 376

7.4 Object Tracking 377

7.4.1 Object Size and Distance Detection 377

7.4.2 Object Tracking with OpenCV 382

Single Object Tracking with OpenCV 382

Multiple Object Tracking with OpenCV 384

7.4.2 Object Tracking with YOLOv4 and DeepSORT 386

7.4.3 Object Tracking with Gluon 389

7.5 Image Segmentation 389

7.5.1 Image Semantic Segmentation and Image Instance Segmentation 390

PexelLib 390

Detectron2 394

Gluon CV 394

7.5.2 K-means Clustering Image Segmentation 394

7.5.3 Watershed Image Segmentation 396

7.6 Background Removal 405

7.6.1 Background Removal with OpenCV 405

7.6.2 Background Removal with PaddlePaddle 423

7.6.3 Background Removal with PixelLib 425

7.7 Depth Estimation 426

7.7.1 Depth Estimation from a Single Image 426

7.7.2 Depth Estimation from Stereo Images 428

7.8 Augmented Reality 430

7.9 Summary 431

7.10 Chapter Review Questions 431

Chapter 8 Pose Detection 433

8.1 Introduction 433

8.2 Hand Gesture Detection 434

8.2.1 OpenCV 434

8.2.2 TensorFlow.js 452

8.3 Sign Language Detection 453

8.4 Body Pose Detection 454

8.4.1 OpenPose 454

8.4.2 OpenCV 455

8.4.3 Gluon 455

8.4.4 PoseNet 456

8.4.5 ML5JS 457

8.4.6 MediaPipe 459

8.5 Human Activity Recognition 461

ActionAI 461

Gluon Action Detection 461

Accelerometer Data HAR 461

8.6 Summary 464

8.7 Chapter Review Questions 464

Chapter 9 GAN and Neural-Style Transfer 465

9.1 Introduction 465

9.2 Generative Adversarial Network 466

9.2.1 CycleGAN 467

9.2.2 StyleGAN 469

9.2.3 Pix2Pix 474

9.2.4 PULSE 475

9.2.5 Image Super-Resolution 475

9.2.6 2D to 3D 478

9.3 Neural-Style Transfer 479

9.4 Adversarial Machine Learning 484

9.5 Music Generation 486

9.6 Summary 489

9.7 Chapter Review Questions 489

Chapter 10 Natural Language Processing 491

10.1 Introduction 491

10.1.1 Natural Language Toolkit 492

10.1.2 spaCy 493

10.1.3 Gensim 493

10.1.4 TextBlob 494

10.2 Text Summarization 494

10.3 Text Sentiment Analysis 508

10.4 Text/Poem Generation 510

10.5.1 Text to Speech 515

10.5.2 Speech to Text 517

10.6 Machine Translation 522

10.7 Optical Character Recognition 523

10.8 QR Code 524

10.9 PDF and DOCX Files 527

10.10 Chatbots and Question Answering 530

10.10.1 ChatterBot 530

10.10.2 Transformers 532

10.10.3 J.A.R.V.I.S. 534

10.10.4 Chatbot Resources and Examples 540

10.11 Summary 541

10.12 Chapter Review Questions 542

Chapter 11 Data Analysis 543

11.1 Introduction 543

11.2 Regression 544

11.2.1 Linear Regression 545

11.2.2 Support Vector Regression 547

11.2.3 Partial Least Squares Regression 554

11.3 Time-Series Analysis 563

11.3.1 Stock Price Data 563

11.3.2 Stock Price Prediction 565

Streamlit Stock Price Web App 569

11.3.4 Seasonal Trend Analysis 573

11.3.5 Sound Analysis 576

11.4 Predictive Maintenance Analysis 580

11.5 Anomaly Detection and Fraud Detection 584

11.5.1 Numenta Anomaly Detection 584

11.5.2 Textile Defect Detection 584

11.5.3 Healthcare Fraud Detection 584

11.5.4 Santander Customer Transaction Prediction 584

11.6 COVID-19 Data Visualization and Analysis 585

11.7 KerasClassifier and KerasRegressor 588

11.7.1 KerasClassifier 589

11.7.2 KerasRegressor 593

11.8 SQL and NoSQL Databases 599

11.9 Immutable Database 608

11.9.1 Immudb 608

11.9.2 Amazon Quantum Ledger Database 609

11.10 Summary 610

11.11 Chapter Review Questions 610

Chapter 12 Advanced AI Computing 613

12.1 Introduction 613

12.2 AI with Graphics Processing Unit 614

12.3 AI with Tensor Processing Unit 618

12.4 AI with Intelligence Processing Unit 621

12.5 AI with Cloud Computing 622

12.5.1 Amazon AWS 623

12.5.2 Microsoft Azure 624

12.5.3 Google Cloud Platform 625

12.5.4 Comparison of AWS, Azure, and GCP 625

12.6 Web-Based AI 629

12.6.1 Django 629

12.6.2 Flask 629

12.6.3 Streamlit 634

12.6.4 Other Libraries 634

12.7 Packaging the Code 635

Pyinstaller 635

Nbconvert 635

Py2Exe 636

Py2app 636

Auto-Py-To-Exe 636

cx_Freeze 637

Cython 638

Kubernetes 639

Docker 642

PIP 647

12.8 AI with Edge Computing 647

12.8.1 Google Coral 647

12.8.2 TinyML 648

12.8.3 Raspberry Pi 649

12.9 Create a Mobile AI App 651

12.10 Quantum AI 653

12.11 Summary 657

12.12 Chapter Review Questions 657

In Practical Artificial Intelligence Programming with Python: From Zero to Hero, veteran educator and photophysicist Dr. Perry Xiao delivers a thorough introduction to one of the most exciting areas of computer science in modern history. The book demystifies artificial intelligence and teaches readers its fundamentals from scratch in simple and plain language and with illustrative code examples.

Divided into three parts, the author explains artificial intelligence generally, machine learning, and deep learning. It tackles a wide variety of useful topics, from classification and regression in machine learning to generative adversarial networks. He also includes:

Fulsome introductions to MATLAB, Python, AI, machine learning, and deep learning
Expansive discussions on supervised and unsupervised machine learning, as well as semi-supervised learning
Practical AI and Python “cheat sheet” quick references
This hands-on AI programming guide is perfect for anyone with a basic knowledge of programming—including familiarity with variables, arrays, loops, if-else statements, and file input and output—who seeks to understand foundational concepts in AI and AI development.