Название: Machine Learning Q and AI: 30 Essential Questions and Answers on Machine Learning and AI
Автор: Sebastian Raschka
Издательство: No Starch Press
Год: 2024
Страниц: 325
Язык: английский
Формат: pdf, epub
Размер: 28.8 MB

If you’re ready to venture beyond introductory concepts and dig deeper into Machine Learning, Deep Learning, and AI, the question-and-answer format of Machine Learning Q and AI will make things fast and easy for you, without a lot of mucking about.

Born out of questions often fielded by author Sebastian Raschka, the direct, no-nonsense approach of this book makes advanced topics more accessible and genuinely engaging. Each brief, self-contained chapter journeys through a fundamental question in AI, unraveling it with clear explanations, diagrams, and hands-on exercises.

This book adopts a unique Q&A style, where each brief chapter is structured around a central question related to fundamental concepts in Machine Learning, Deep Learning, and AI. Every question is followed by an explanation, with several illustrations and figures, as well as exercises to test your understanding. Many chapters also include references for further reading. These bite-sized nuggets of information provide an enjoyable jumping-off point on your journey from Machine Learning beginner to expert.

The book covers a wide range of topics. It includes new insights about established architectures, such as convolutional networks, that allow you to utilize these technologies more effectively. It also discusses more advanced techniques, such as the inner workings of large language models (LLMs) and vision transformers. Even experienced Machine Learning researchers and practitioners will encounter something new to add to their arsenal of techniques.
While this book will expose you to new concepts and ideas, it’s not a math or coding book. You won’t need to solve any proofs or run any code while reading. In other words, this book is a perfect travel companion or something you can read on your favorite reading chair with your morning coffee or tea.

What's inside:

Focused Chapters: Key questions in AI are answered concisely, and complex ideas are broken down into easily digestible parts.

Wide Range of Topics: Raschka covers topics ranging from neural network architectures and model evaluation to computer vision and natural language processing.

Practical Applications: Learn techniques for enhancing model performance, fine-tuning large models, and more.

You’ll also explore how to:
• Manage the various sources of randomness in neural network training
• Differentiate between encoder and decoder architectures in large language models
• Reduce overfitting through data and model modifications
• Construct confidence intervals for classifiers and optimize models with limited labeled data
• Choose between different multi-GPU training paradigms and different types of generative AI models
• Understand performance metrics for natural language processing
• Make sense of the inductive biases in vision transformers

Who Is This Book For?
Navigating the world of AI and Machine Learning literature can often feel like walking a tightrope, with most books positioned at either end: broad beginner’s introductions or deeply mathematical treatises. This book illustrates and discusses important developments in these fields while staying approachable and not requiring an advanced math or coding background. This book is for people with some experience with Machine Learning who want to learn new concepts and techniques. It’s ideal for those who have taken a beginner course in Machine Learning or Deep Learning or have read an equivalent introductory book on the topic. (Throughout this book, I will use Machine Learning as an umbrella term for Machine Learning, Deep Learning, and AI.)