A Beginner's Guide to Generative AI - (Synthesis Lectures on Computer Science) (Hardcover)

Book Synopsis

This book is the essential guide for anyone curious about AI's creative power. In the rapidly evolving landscape of artificial intelligence, generative AI stands out as one of the most transformative technologies of our time. Designed for beginners and requiring no prior knowledge of AI, this book breaks down the fundamentals of generative AI, from text and image generation to the workings of models like ChatGPT and Google Bard. The authors provide step-by-step coverage of the essential concepts and techniques that power generative AI. From the basics of how machines learn to generate text and images, to the intricate workings of models like Transformers, ChatGPT, and Google Bard, readers will gain a solid foundation in AI's most cutting-edge tools. Rather than focusing on a single method, the authors introduce a spectrum of generative modeling techniques, including diffusion models, variational autoencoders, and transformers. This comprehensive exposure ensures readers will be well-prepared to understand and adapt to the rapidly evolving AI landscape. In addition, real-world applications of generative AI across various industries are explored including healthcare innovations, business analytics, and legal technology, and the authors provide practical insights and examples that show how generative AI is revolutionizing these fields.

From the Back Cover

This book is the essential guide for anyone curious about AI's creative power. In the rapidly evolving landscape of artificial intelligence, generative AI stands out as one of the most transformative technologies of our time. Designed for beginners and requiring no prior knowledge of AI, this book breaks down the fundamentals of generative AI, from text and image generation to the workings of models like ChatGPT and Google Bard. The authors provide step-by-step coverage of the essential concepts and techniques that power generative AI. From the basics of how machines learn to generate text and images, to the intricate workings of models like Transformers, ChatGPT, and Google Bard, readers will gain a solid foundation in AI's most cutting-edge tools. Rather than focusing on a single method, the authors introduce a spectrum of generative modeling techniques, including diffusion models, variational autoencoders, and transformers. This comprehensive exposure ensures readers will be well-prepared to understand and adapt to the rapidly evolving AI landscape. In addition, real-world applications of generative AI across various industries are explored including healthcare innovations, business analytics, and legal technology, and the authors provide practical insights and examples that show how generative AI is revolutionizing these fields.

In addition, this book:

• Offers a thorough, accessible, and engaging introduction to one of the most exciting areas of technology today
• Covers a diverse range of generative modeling techniques, from transformers to variational autoencoders
• Includes multiple-choice exercise questions and summaries at the end of each chapter to reinforce learning

About the Author

Deepshikha Bhati is a Lecturer in the Department of Computer Science at Kent State University. Prior to her current role, she built a strong foundation in both industry and academia, holding various teaching and research positions. Her academic journey includes deep expertise in generative AI LLM models, explainable AI (XAI), information visualization, image processing, deep learning (DL), and machine learning (ML). Ms. Bhati is a member of IEEE, the IEEE Computer Society, and ACM.

Fnu Neha is a Ph.D. candidate in the Department of Computer Science at Kent State University, with over six years of experience in research and teaching, particularly in artificial intelligence (AI), deep learning, and databases. Her Ph.D. research focuses on developing deep learning techniques and AI-based software to analyze renal CT scans and correlate them with radiography and biopsy-based features for the accurate classification of small renal masses and subtypes of renal cell carcinoma (RCC).

Angela Guercio, Ph.D., is an Associate Professor of Computer Science at Kent State University, where she has worked for 19 years. Prior to joining Kent State University, she served as an Assistant Professor at Hiram College for three years and as a Senior Research Associate at the University of Salerno, Italy, for 16 years. Her research interests include smart e-education and AI, big data, data mining, software engineering, visual languages, human-machine interaction, and multimedia computing. She has co-authored numerous papers published in scientific journals and refereed international conferences. Dr. Guercio has received multiple research awards and fellowships for her work. Dr. Guercio is a member of IEEE, the IEEE Computer Society, and ACM.

Md Amiruzzaman, Ph.D., is an Assistant Professor in the Department of Computer Science at West Chester University. Before joining West Chester University, he worked as a software developer for almost 10 years for several companies. He has also held the position of Assistant Professor at Kent State University. In the past, he has worked as a Research Assistant at Sejong University and Korea University. His research interests include visual analytics of urban data, data mining, machine learning, deep learning, and data hiding.

Aloysius Bathi Kasturiarachi, Ph.D. has been at Kent State University since 1995 as a faculty member in the Department of Mathematical Sciences. He teaches courses in mathematics and computer science. He won the Distinguished Teaching Award in 2001 and was a finalist in 2022. He is the recipient of numerous grants. He also served as the Associate Dean for Academic Affairs at Kent State University at Stark from August 2013 to January 2018. His research interests include partial differential equations, non-integrable systems, numerical analysis, mathematics education, and number theory. He has published extensively in these areas. He is a member of MAA and AMS.