Applied Generative AI for Beginners: Practical Knowledge on Diffusion Models, ChatGPT, and Other LLMs

by Akshay Kulkarni, Adarsha Shivananda, Anoosh Kulkarni

This book provides a deep dive into the world of generative AI, covering everything from the basics of neural networks to the intricacies of large language models like ChatGPT and Google Bard. It serves as a one-stop resource for anyone interested in understanding and applying this transformative technology and is particularly aimed at those just getting started with generative AI. Applied Generative AI for Beginners is structured around detailed chapters that will guide you from foundational knowledge to practical implementation. It starts with an introduction to generative AI and its current landscape, followed by an exploration of how the evolution of neural networks led to the development of large language models. The book then delves into specific architectures like ChatGPT and Google Bard, offering hands-on demonstrations for implementation using tools like Sklearn. You’ll also gain insight into the strategic aspects of implementing generative AI in an enterprise setting, with the authors covering crucial topics such as LLMOps, technology stack selection, and in-context learning. The latter part of the book explores generative AI for images and provides industry-specific use cases, making it a comprehensive guide for practical application in various domains. Whether you're a data scientist looking to implement advanced models, a business leader aiming to leverage AI for enterprise growth, or an academic interested in cutting-edge advancements, this book offers a concise yet thorough guide to mastering generative AI, balancing theoretical knowledge with practical insights. What You Will Learn Who This Book Is For Data scientists, AI practitioners, Researchers and software engineers interested in generative AI and LLMs.

228 pages, Paperback

Published November 22, 2023

Reviews

[Artur Klauser · Rating 2 out of 5]

Yet again, I find that the quality of books from Apress is highly variable, and this one falls on the lower end of the spectrum. There is insufficient coordination between the chapters (co-authors?) often repeating the most basic things over and over, which just turn to useless page fillers after the first time. Also the "practical" part highly disappoints. All it does is showing the usage of some python library accessing the (pay per use) OpenAi API. The very same examples, by the way, that the intro documentation for the library provides itself, online and for free. What I had expected instead were examples using basic machine learning libraries (PyTorch, Tensor Flow, or what have you) that would allow the reader to gain deeper insight into how those LLM algorithms work. But that is nowhere to be found. Instead large parts of the book are covered in a representative litany of potential LLM use cases, mostly in business settings, without really going into much depth on any of those either.
If you look for understanding of LLMs and their capabilities it seems the plethora of existing online blog posts gets you much farther than reading this book does.

[عباد ديرانية · Rating 2 out of 5]

I like the premise and organization of the book, as it helped introduce me to a ton of concepts I never had knolwedge of. Describing it as "for beginners", however, is a huge misexpectation. I already have a good foundation in AI from ML courses in Python as well as general reading on AI, yet this book was often very confusing. As a book that claims to be for beginners, its explanations are awfully often recursive: an "encoder" encodes, self-attention is attention to the self-token, and the key vector is the key to which the query attends. The transformer architecture chapter left me Googling and Youtubing a dozen concepts, then ended up more confused than before I started it.

[Kristen Considine · Rating 2 out of 5]

This was a difficult read for me as I’m not a developer or have that kind of mind and I found it hard to stay focused to absorb the material. However, it was a basic overview and I appreciated the use case examples and comparisons across models and architecture types.

[Ravi Naidu · Rating 4 out of 5]

Enjoyed reading the book in a quick read format, explained well enough to get started on LLM