This book provides a straightforward look at the concepts, algorithms and advantages of Bayesian Deep Learning and Deep Generative Models. Starting from the model-based approach to Machine Learning, the authors motivate Probabilistic Graphical Models and show how Bayesian inference naturally lends itself to this framework. The authors present detailed explanations of the main modern algorithms on variational approximations for Bayesian inference in neural networks. Each algorithm of this selected set develops a distinct aspect of the theory. The book builds from the ground-up well-known deep…mehr
This book provides a straightforward look at the concepts, algorithms and advantages of Bayesian Deep Learning and Deep Generative Models. Starting from the model-based approach to Machine Learning, the authors motivate Probabilistic Graphical Models and show how Bayesian inference naturally lends itself to this framework. The authors present detailed explanations of the main modern algorithms on variational approximations for Bayesian inference in neural networks. Each algorithm of this selected set develops a distinct aspect of the theory. The book builds from the ground-up well-known deep generative models, such as Variational Autoencoder and subsequent theoretical developments. By also exposing the main issues of the algorithms together with different methods to mitigate such issues, the book supplies the necessary knowledge on generative models for the reader to handle a wide range of data types: sequential or not, continuous or not, labelled or not. The book is self-contained, promptly covering all necessary theory so that the reader does not have to search for additional information elsewhere.
Offers a concise self-contained resource, covering the basic concepts to the algorithms for Bayesian Deep Learning;Presents Statistical Inference concepts, offering a set of elucidative examples, practical aspects, and pseudo-codes;Every chapter includes hands-on examples and exercises and a website features lecture slides, additional examples, and other support material.
Lucas P. Cinelli was born in Rio de Janeiro, Brazil. He received the Electronics and Computer Engineering degree from the Universidade Federal do Rio de Janeiro (UFRJ), as well as the Engineering degree with major in Electronic Systems, Networks & Images from the Grande École Supélec, in France, due to his academic exchange in 2014-2016. During this period, he also received the Master's degree in Microtechnologies, Architecture, Communication Networks and Systems from Supélec/INSA-Rennes. In 2019, he received the M.Sc. degree in Electrical Engineering from COPPE/UFRJ, for his dissertation on variational methods for machine learning and is currently pursuing his Ph.D. degree at the same institution. His research on anomaly detection in videos with deep learning alongside his colleagues has led to publications on ICIP 2018 and a Brazilian conference (SBrT) in 2017. Matheus A. Marins was born in Rio de Janeiro, Brazil. He received the Electronics and Computer Engineering degree from the Universidade Federal do Rio de Janeiro (UFRJ), in 2016, having done a one-year exchange program at Illinois Institute of Technology (IIT), in the Computer Engineering course. He received the M.Sc. degree in Electrical Engineering from COPPE/UFRJ in 2018, being awarded with a scholarship for his academic performance by the Rio de Janeiro State government. Currently, he is pursuing his Ph.D. degree at the same institution and has shifted his research towards modern Bayesian methods applied to Machine Learning. So far, his research has been focused on Machine Learning, especially on condition-based models to identify and prevent failures on physical systems, which resulted on two international journals (2017 and 2020) and on a Brazilian conference paper (SBrT). Eduardo A. B. da Silva was born in Rio de Janeiro, Brazil. He received the Electronics Engineering degree from Instituto Militar de Engenharia (IME), Brazil, in 1984, the M.Sc. degree in Electrical Engineering from Universidade Federal do Rio de Janeiro (COPPE/UFRJ) in 1990, and the Ph.D. degree in Electronics from the University of Essex, England, in 1995. He is a professor at Universidade Federal do Rio de Janeiro since 1989. He is co-author of the book "Digital Signal Processing - System Analysis and Design", published by Cambridge University Press. He published more than 70 papers in international journals. His research interests lie in the fields of signal and image processing, signal compression, 3D videos, computer vision, light fields and machine learning, together with its applications to telecommunications and the oil and gas industry. He is co-editor of the future standard ISO/IEC CD 21794-2, JPEG Pleno Plenoptic image coding system, and is currently Requirements Vice Chair of JPEG. Sergio L. Netto was born in Rio de Janeiro, Brazil. He received the B.Sc. (cum laude) degree from the Universidade Federal do Rio de Janeiro (UFRJ), Brazil, in 1991, the M.Sc. degree from COPPE/UFRJ in 1992, and the Ph.D. degree from the University of Victoria, BC, Canada, in 1996, all in electrical engineering. Since 1997, he has been with the Department of Electronics and Computer Engineering, Poli/UFRJ, and since 1998, he has been with the Program of Electrical Engineering, COPPE/UFRJ. He is the Co-Author (with P. S. R. Diniz and E. A. B. da Silva) of Digital Signal Processing: System Analysis and Design (Cambridge University Press, 2nd edition, 2010), which has also been translated to Chinese and Portuguese. His research and teaching interests lie in the areas of digital signal processing,speech processing, information theory, and computer vision. Prof. Netto received the 2006 Guillemin-Cauer award from the IEEE Circuits and Systems Society for the best paper published in the year of 2005 in the IEEE Trans. Circuits and Systems, Part I: Regular Papers.
Inhaltsangabe
Introduction.- Fundamentals of Statistical Inference.- Model-Based Machine Learning and Approximate Inference.- Bayesian Neural Networks.- Variational Autoencoders.- Conclusion.
Introduction.- Fundamentals of Statistical Inference.- Model-Based Machine Learning and Approximate Inference.- Bayesian Neural Networks.- Variational Autoencoders.- Conclusion.
