Machine Unlearning: Concepts, Techniques and Applications

This book masters the critical skill of selective data removal from AI systems essential for regulatory compliance and ethical AI development. This comprehensive book bridges the gap between theoretical foundations and practical implementation, offering clear pathways through both exact and approximate unlearning methodologies. Designed for machine learning engineers, privacy specialists, researchers, and policymakers, it uniquely integrates technical depth with legal and ethical frameworks. From telecom to finance, discover how to eliminate data influence while preserving model utility. Ideal for graduate courses, professional training, and organizational compliance initiatives, this book positions you at the forefront of responsible AI innovation in an increasingly privacy-conscious world.

Riassunto

This book masters the critical skill of selective data removal from AI systems—essential for regulatory compliance and ethical AI development. This comprehensive book bridges the gap between theoretical foundations and practical implementation, offering clear pathways through both exact and approximate unlearning methodologies. Designed for machine learning engineers, privacy specialists, researchers, and policymakers, it uniquely integrates technical depth with legal and ethical frameworks. From telecom to finance, discover how to eliminate data influence while preserving model utility. Ideal for graduate courses, professional training, and organizational compliance initiatives, this book positions you at the forefront of responsible AI innovation in an increasingly privacy-conscious world.

Dettagli sul prodotto

• Autori: Rajan Gupta, Anamika Gupta, Sarabjeet Kaur Kochhar, Saibal K. Pal, Sarabjeet Kau Kochhar
• Editore: Springer, Berlin
• Contenuto: Libro
• Forma del prodotto: Copertina rigida
• Data pubblicazione: 24.05.2026
• Categoria: Scienze naturali, medicina, informatica, tecnica > Tecnica > Tematiche generali, enciclopedie
• EAN: 9783032184467
• ISBN: 978-3-0-3218446-7
• Numero di pagine: 197
• Illustrazioni: XXV, 197 p.
• Dimensioni (della confezione): 15.5 x 23.5 cm
• Serie: Studies in Computational Intelligence > 1270
• Categorie: machine learning, Maschinelles Lernen, Deep Learning, right to be forgotten, Computational Intelligence, Machine Unlearning, recommendation systems, Knowledge Graphs, Federated Learning, Privacy Preservation, Bayesian methods, Graph Neural Networks, GDPR Compliance, Data Deletion, SISA Framework, Approximate Unlearning, Influence Functions, Exact Unlearning, Model Editing, Gradient-based Unlearning, Neural Network Editing