Machine Learning Q and AI

✍ Scribed by Sebastian Raschka, PhD

• Publisher: leanpub.com
• Year: 2023
• Tongue: English
• Leaves: 231
• Category: Library

✦ Table of Contents

Table of Contents
Preface
Who Is This Book For?
What Will You Get Out of This Book?
How To Read This Book
Discussion Forum
Sharing Feedback and Supporting This Book
Acknowledgements
About the Author
Copyright and Disclaimer
Credits
Introduction
Chapter 1. Neural Networks and Deep Learning
Q1. Embeddings, Representations, and Latent Space
Q2. Self-Supervised Learning
Q3. Few-Shot Learning
Q4. The Lottery Ticket Hypothesis
Q5. Reducing Overfitting with Data
Q6. Reducing Overfitting with Model Modifications
Q7. Multi-GPU Training Paradigms
Q8. The Keys to Success of Transformers
Q9. Generative AI Models
Q10. Sources of Randomness
Chapter 2. Computer Vision
Q11. Calculating the Number of Parameters
Q12. The Equivalence of Fully Connected and Convolutional Layers
Q13. Large Training Sets for Vision Transformers
Chapter 3. Natural Language Processing
Q15. The Distributional Hypothesis
Q16. Data Augmentation for Text
Q17. ``Self''-Attention
Q18. Encoder- And Decoder-Style Transformers
Q19. Using and Finetuning Pretrained Transformers
Q20. Evaluating Generative Language Models
Chapter 4. Production, Real-World, And Deployment Scenarios
Q21. Stateless And Stateful Training
Q22. Data-Centric AI
Q23. Speeding Up Inference
Chapter 5. Predictive Performance and Model Evaluation
Q25. Poisson and Ordinal Regression
Q27. Proper Metrics
Q28. The k in k-fold cross-validation
Q29. Training and Test Set Discordance
Q30. Limited Labeled Data
Afterword
Appendix A: Reader Quiz Solutions
Appendix B: List of Questions