000			01792nam a22002417a 4500
005			20260610111006.0
008			260610s2026 |||||||| |||| 00| 0 eng d
020			_a9783031970061
040			_cPK-LaUMT
082			_a006.33 _bEXP-
245	0	0	_aExplainable artificial intelligence for trustworthy decisions in smart applications / _cedited by Nicu Bizon and Bhargav Appasani
260			_aCham : _bSpringer, _c2026
300			_axii, 415 p.
500			_aIncludes bibliographical references.
520			_aThis book introduces readers to the field of explainable artificial intelligence (XAI), which aims to make AI models more transparent and trustworthy. It explores how XAI can enhance trust and confidence in AI models and their decisions across various innovative applications in fields such as healthcare, finance, and engineering, where AI can significantly impact quality of life. Readers will discover emerging trends related to XAI—such as large language models, generative AI, and natural language processing—that are transforming the landscape of AI research and applications. Featuring an interdisciplinary overview, the book examines the state of the art, challenges, and opportunities in XAI, accompanied by clear examples and detailed explanations of its methods and techniques. The book also offers a balanced perspective on the limitations and trade-offs of XAI and outlines future directions and opportunities for both research and practice. This book is intended for anyone who wants to learn more about XAI and understand how it can enhance trust in AI models
546			_aEng
650			_aExplainable-AI _912645
650			_aMachine learning
650			_aTrust
700	1		_aBizon, Nicu _912646
700	1		_aAppasani, Bhargav _912647
942			_cBK
999			_c141095 _d141095