Learning from Data with the Maximum Correntropy Criterion

Inbunden, Engelska, 2026

AvBadong Chen,Lei Xing,Nanning Zheng,José C. Principe

2 269 kr

Kommande

Traditional signal processing and machine learning methods rely on mean square error, which becomes brittle when data contains heavy-tailed noise, impulsive disturbances, and outliers-conditions frequently encountered in real-world applications. This comprehensive guidebook introduces correntropy-based methods that demonstrate superior robustness across diverse engineering domains, progressing from foundational concepts to applications. Authored by pioneers in information theoretic learning, the book systematically covers correntropy fundamentals, adaptive filtering techniques, neural network training, feature learning, and applications including point set registration, matrix completion, and federated learning. Each chapter balances rigorous theory with practical algorithms and performance comparisons against conventional methods. With implementation guidelines and a unified framework connecting different robust learning criteria, this book addresses the critical gap between Gaussian-assumption theory and non-Gaussian reality, providing researchers and graduate students with applicable solutions for challenging real-world problems.

Produktinformation

Utgivningsdatum2026-12-31
FormatInbunden
SpråkEngelska
Antal sidor326
FörlagCambridge University Press
ISBN9781009366687

Tillhör följande kategorier

Systemvetenskap och AI inom Data och IT

Badong Chen is Professor at the State Key Laboratory of Human-Machine Hybrid Augmented Intelligence, Institute of Artificial Intelligence and Robotics, Xi'an Jiaotong University. He has authored seven books and more than 300 publications in machine learning, brain-inspired intelligence, and brain-machine interfaces. He has served as Associate Editor for IEEE TNNLS, IEEE TCSVT, and Neural Networks. Lei Xing is Assistant Professor at the State Key Laboratory of Human-Machine Hybrid Augmented Intelligence, Institute of Artificial Intelligence and Robotics, Xi'an Jiaotong University. His research focuses on robust machine learning and multi-view learning. Nanning Zheng (Life Fellow, IEEE) is Professor and Director of the State Key Laboratory of Human-Machine Hybrid Augmented Intelligence, Institute of Artificial Intelligence and Robotics, Xi'an Jiaotong University, and a member of the Chinese Academy of Engineering. He has served as Chinese Representative on the Governing Board of the International Association for Pattern Recognition since 2000. Jose C. Principe (Life Fellow, IEEE) is Distinguished Professor at the University of Florida and Director of the Computational NeuroEngineering Laboratory, and an AAAS, AIMBE and NAI Fellow. He has authored more than 900 publications and supervised 108 PhD dissertations. He received the IEEE Neural Network Pioneer Award, the IEEE Shannon-Nyquist Technical Achievement Award from the Signal Processing Society, and the IEEE Career Award from the EMB Society.

Preface; 1. Introduction; 2. Maximum correntropy criterion; 3. Linear adaptive filters under maximum correntropy criterion; 4. Nonlinear adaptive filters under maximum correntropy criterion; 5. Kalman filters under maximum correntropy criterion; 6. Neural networks training under maximum correntropy criterion; 7. Feature learning and subspace clustering under maximum correntropy criterion; 8. Point set registration under maximum correntropy criterion; 9. Additional topics in correntropy based learning; 10. From maximum correntropy criterion to minimum error entropy criterion; Bibliography; Index.