Textbook in PDF format

This book begins with an overview of the Generative AI landscape, distinguishing it from conversational AI and shedding light on the roles of key players like DeepMind and OpenAI. It then reviews the intricacies of ChatGPT, GPT-4, Meta AI, Claude 3, and Gemini, examining their capabilities, strengths, and competitors. Readers will also gain insights into the BERT family of LLMs, including ALBERT, DistilBERT, and XLNet, and how these models have revolutionized natural language processing. Further, the book covers prompt engineering techniques, essential for optimizing the outputs of AI models, and addresses the challenges of working with LLMs, including the phenomenon of hallucinations and the nuances of fine-tuning these advanced models. Designed for software developers, AI researchers, and technology enthusiasts with a foundational understanding of AI, this book offers both theoretical insights and practical code examples in Python. Companion files with code, figures, and datasets are available for downloading from the publisher with Amazon proof of purchase.
The first chapter serves as an introduction to Generative AI, setting the stage for a deeper exploration into the subject. It provides a clear definition and understanding of generative AI, drawing distinctions between it and conversational AI. This chapter not only introduces pivotal AI entities like DALL-E, ChatGPT-3, GPT-4, and DeepMind but also elucidates their functionalities and groundbreaking contributions. Further, it considers the intricacies of LLMs, offering insights into their language comprehension capabilities, model sizes, and training methodologies.
The second chapter is dedicated to ChatGPT and GPT-4, along with a description of GPT-4o that was released on May 13, 2024. You will also learn about some of the competitors to ChatGPT and GPT-4o.
The third chapter provides an overview of BERT and the BERT family of LLMs, which comprises an extensive set of LLMs, such as ALBERT, DistilBERT, and XLNET (among many others).
Chapter 4 discusses prompt engineering techniques, starting with an explanation of prompts and completions, followed by a discussion of prompt categories, instruction prompts, and prompt templates. You will also learn about various aspects of Chain of Thought (CoT) prompts, Tree of Thought (ToT) prompts, and Buffer of Thoughts (BoT) prompts.
Chapter 5 looks into so-called hallucinations that occur with every LLM, along with suggestions - provided by various LLMs - for reducing hallucinations. This chapter also discusses small language models (SLMs), and an introduction to AI agents.
The sixth chapter discusses fine tuning of LLMs, which is another very important topic, and the seventh chapter is dedicated to code samples for SVG that are generated by GPT-4. The last chapter contains miscellaneous generative AI topics, such as bias mitigation, ethical and safety issues, quantum computing and AI, and some future trends in Generative AI.
Whether you’re a seasoned AI researcher or a curious enthusiast, this detailed table of contents serves as a roadmap to the world of Transformers, BERT, and GPT, guiding you through their inception, evolution, and future potential