Deep Generative Modeling

This textbook combines probabilistic modeling and deep learning to formulate AI systems, called deep generative modeling. It assumes that each phenomenon is driven by an underlying generative process and utilizes deep neural networks to parameterize distributions. Probability theory provides a unified framework for quantifying uncertainty and defining objective functions. The book is designed for students, engineers, and researchers with a modest mathematical background and introduces fundamental concepts with specific examples and code snippets.

Format: Paperback / softback
Length: 197 pages
Publication date: 19 February 2023
Publisher: Springer Nature Switzerland AG

This comprehensive textbook delves into the intricate realm of formulating Artificial Intelligence (AI) systems by seamlessly integrating probabilistic modeling and deep learning techniques. Moreover, it surpasses conventional predictive modeling by seamlessly combining supervised learning and unsupervised learning. The resultant paradigm, known as deep generative modeling, adopts a generative perspective to perceive the surrounding world. It assumes that each phenomenon is driven by an underlying generative process that defines a joint distribution over random variables and their stochastic interactions, elucidating how events occur and in what sequence. The term "deep" in deep generative modeling stems from the fact that the distribution is parameterized using deep neural networks.

One of the distinguishing features of deep generative modeling is its ability to employ deep neural networks, enabling the rich and flexible parameterization of distributions. This flexibility allows for the representation of complex and diverse phenomena, enabling a more comprehensive understanding of the underlying data. Furthermore, the principled approach to modeling stochastic dependencies using probability theory ensures rigorous formulation and prevents potential flaws in reasoning. Probability theory serves as a unifying framework where the likelihood function assumes a pivotal role in quantifying uncertainty and defining objective functions.

Deep Generative Modeling is meticulously crafted to cater to the interests of curious students, engineers, and researchers with a foundational mathematical background in undergraduate calculus, linear algebra, probability theory, and the fundamentals of machine learning, deep learning, and programming in Python and PyTorch (or other deep learning libraries). Its appeal extends to students and researchers from diverse backgrounds, including computer science, engineering, data science, physics, and bioinformatics, who aspire to gain proficiency in deep generative modeling. To engage the reader, the book introduces fundamental concepts with specific examples, fostering a deeper understanding and practical application of these advanced techniques.

Weight: 337g
Dimension: 235 x 155 (mm)
ISBN-13: 9783030931605
Edition number: 1st ed. 2022