Originating from lectures delivered at the African Institute of Mathematical Sciences, this book presents a unifying perspective on traditional and modern methods in generative AI and stochastic thermodynamics. By relating the core topics in machine learning to the notion of (variational) free-energy, a bridge is built between methods such as latent variable models, variational auto-encoders, optimal control, optimal transport, normalizing flows and diffusion models and concepts such as entropy production and fluctuation theorems in stochastic thermodynamics. Structured into three main parts, the book commences by setting up the required mathematical and statistical physics preliminaries needed to make it broadly accessible. The largest part of the book then focuses on building intuition of major advances in generative AI by considering discrete time processes and their relationship to topics in stochastic thermodynamics. Finally, the authors take a short excursion to the continuous time domain for the more advanced learner.
"synopsis" may belong to another edition of this title.
Max Welling is the co-founder and Chief Technology Officer of the startup CuspAI, and a Full Professor of Machine Learning at the University of Amsterdam. He is a member of the Dutch Royal Academy of Sciences and the Canadian Institute for Advanced Research, and a fellow of the European Lab for Learning and Intelligent Systems. Professor Welling received the ECCV Koenderink Prize in 2010, the 2021 ICML Test of Time Award, and the 2024 ICLR Test of Time Award.
Sirui Lu is a doctoral researcher at the Max Planck Institute of Quantum Optics, Germany. His research focuses on the intersection of (quantum) physics and artificial intelligence. He previously earned his master's and bachelor's degrees in physics from the Technical University of Munich and Tsinghua University, Beijing, respectively.
Lars Holdijk is a PhD student at the University of Oxford. His research focuses on the intersection of generative artificial intelligence, computational biochemistry, and statistical physics.
"About this title" may belong to another edition of this title.
Seller: Books Puddle, New York, NY, U.S.A.
Condition: New. Seller Inventory # 26405778932
Seller: Kennys Bookstore, Olney, MD, U.S.A.
Condition: New. 2026. hardcover. . . . . . Books ship from the US and Ireland. Seller Inventory # V9781009709064
Seller: Majestic Books, Hounslow, United Kingdom
Condition: New. Print on Demand. Seller Inventory # 408423979
Quantity: 4 available
Seller: Kennys Bookshop and Art Galleries Ltd., Galway, GY, Ireland
Condition: New. 2026. hardcover. . . . . . Seller Inventory # V9781009709064
Quantity: Over 20 available
Seller: CitiRetail, Stevenage, United Kingdom
Hardcover. Condition: new. Hardcover. Originating from lectures delivered at the African Institute of Mathematical Sciences, this book presents a unifying perspective on traditional and modern methods in generative AI and stochastic thermodynamics. By relating the core topics in machine learning to the notion of (variational) free-energy, a bridge is built between methods such as latent variable models, variational auto-encoders, optimal control, optimal transport, normalizing flows and diffusion models and concepts such as entropy production and fluctuation theorems in stochastic thermodynamics. Structured into three main parts, the book commences by setting up the required mathematical and statistical physics preliminaries needed to make it broadly accessible. The largest part of the book then focuses on building intuition of major advances in generative AI by considering discrete time processes and their relationship to topics in stochastic thermodynamics. Finally, the authors take a short excursion to the continuous time domain for the more advanced learner. Bridging the gap between stochastic thermodynamics and generative AI, this book will interest those working in either discipline, as well as physicists hoping to enter the field of AI. It covers the fundamental concepts before progressing to more advanced methods and encourages the reader to build their intuition. This item is printed on demand. Shipping may be from our UK warehouse or from our Australian or US warehouses, depending on stock availability. Seller Inventory # 9781009709064
Quantity: 1 available
Seller: Revaluation Books, Exeter, United Kingdom
Hardcover. Condition: Brand New. 307 pages. 6.69x0.75x9.61 inches. In Stock. Seller Inventory # x-1009709062
Quantity: 2 available
Seller: Biblios, Frankfurt am main, HESSE, Germany
Condition: New. PRINT ON DEMAND. Seller Inventory # 18405778942
Quantity: 4 available
Seller: AHA-BUCH GmbH, Einbeck, Germany
Buch. Condition: Neu. Neuware - Originating from lectures delivered at the African Institute of Mathematical Sciences, this book presents a unifying perspective on traditional and modern methods in generative AI and stochastic thermodynamics. By relating the core topics in machine learning to the notion of (variational) free-energy, a bridge is built between methods such as latent variable models, variational auto-encoders, optimal control, optimal transport, normalizing flows and diffusion models and concepts such as entropy production and fluctuation theorems in stochastic thermodynamics. Structured into three main parts, the book commences by setting up the required mathematical and statistical physics preliminaries needed to make it broadly accessible. The largest part of the book then focuses on building intuition of major advances in generative AI by considering discrete time processes and their relationship to topics in stochastic thermodynamics. Finally, the authors take a short excursion to the continuous time domain for the more advanced learner. Seller Inventory # 9781009709064
Quantity: 2 available