Introduction 1. AI in a Nutshell 1.1 Defining AI 1.2 A Brief History of AI 1.3 Neural Networks 1.4 Datasets, Training and Testing 2. The Process 2.1 Data Collection 2.

2 Data Preprocessing 2.3 Data Splitting and Augmentation 2.4 Architecture Selection and Training 2.5 Using the Validation Set 2.6 Final Testing and Deployment 3. Configuring the Desktop Environment 3.1 Introducing the Toolkits 3.2 Configuring Linux 3.

3 Configuring macOS 3.4 Configuring Windows 4. Building a Bird Dataset 4.1 Planning, Acquiring and Preprocessing 4.2 Building Train and Test Sets 4.3 Initial Testing 4.4 Reviewing the Code 4.5 Discussion 5.

Exploring the Bird6 Dataset 5.1 Exploring Hyperparameters 5.2 Data Augmentation 5.3 Decision Thresholds 5.4 Ensembling 5.5 Discussion 6. Using Pretrained Models 6.1 Understanding Transfer Learning and Fine Tuning 6.

2 Using Birds 25 6.3 Using ResNet-50 and MobileNet 6.4 Using CLIP 6.5 Discussion 7. Generic Bird Classifiers 7.1 North American Bird Features 7.2 Using NA Bird Features 7.3 Understanding the Models 7.

4 Generic Images and Text 7.5 Discussion 8. Detection 8.1 The Detection Hierarchy 8.2 Experiment: CLIP Embeddings 8.3 Experiment: Fully Convolutional Networks 8.4 Discussion 9. Classifying Audio 9.

1 Sonograms 9.2 A CLIP-tastrophe 9.3 A Transfer Learning Exercise 9.4 Preparing the BirdCLEF Dataset 9.5 Training BirdCLEF from Scratch 9.6 BirdCLEF Transfer Learning 9.7 BirdCLEF Fine-Tuning 9.8 Discussion 10.

Open Source Birding with AI 10.1 Merlin 10.2 eBird 10.3 BirdNET 11. Going Further 11.1 Topics for Further Study 11.2 Recommended Books 11.3 Online Resources and Communities 11.

4 The Future of Birding with AI Glossary Index.