國立虎尾科技大學 |

Robust explainable AI

紀錄類型:	書目-語言資料,印刷品 : Monograph/item
正題名/作者:	Robust explainable AI/ by Francesco Leofante, Matthew Wicker.
作者:	Leofante, Francesco.
其他作者:	Wicker, Matthew.
出版者:	Cham :Springer Nature Switzerland : : 2025.,
面頁冊數:	xii, 71 p. :ill. (some col.), digital ; : 24 cm.;
Contained By:	Springer Nature eBook
標題:	Artificial intelligence. -
電子資源:	https://doi.org/10.1007/978-3-031-89022-2
ISBN:	9783031890222

Robust explainable AI
Leofante, Francesco.

Robust explainable AI[electronic resource] /by Francesco Leofante, Matthew Wicker. - Cham :Springer Nature Switzerland :2025. - xii, 71 p. :ill. (some col.), digital ;24 cm. - SpringerBriefs in intelligent systems. Artificial intelligence, multiagent systems, and cognitive robotics,2196-5498. - SpringerBriefs in intelligent systems.Artificial intelligence, multiagent systems, and cognitive robotics..

Foreword -- Preface -- Acknowledgements -- 1. Introduction -- 2. Explainability in Machine Learning: Preliminaries & Overview -- 3. Robustness of Counterfactual Explanations -- 4. Robustness of Saliency-Based Explanations.

The area of Explainable Artificial Intelligence (XAI) is concerned with providing methods and tools to improve the interpretability of black-box learning models. While several approaches exist to generate explanations, they are often lacking robustness, e.g., they may produce completely different explanations for similar events. This phenomenon has troubling implications, as lack of robustness indicates that explanations are not capturing the underlying decision-making process of a model and thus cannot be trusted. This book aims at introducing Robust Explainable AI, a rapidly growing field whose focus is to ensure that explanations for machine learning models adhere to the highest robustness standards. We will introduce the most important concepts, methodologies, and results in the field, with a particular focus on techniques developed for feature attribution methods and counterfactual explanations for deep neural networks. As prerequisites, a certain familiarity with neural networks and approaches within XAI is desirable but not mandatory. The book is designed to be self-contained, and relevant concepts will be introduced when needed, together with examples to ensure a successful learning experience.

ISBN: 9783031890222

Standard No.: 10.1007/978-3-031-89022-2doiSubjects--Topical Terms:

559380
Artificial intelligence.

LC Class. No.: Q335 / .L46 2025

Dewey Class. No.: 006.3

Robust explainable AI
LDR:02554nam a22003375a 4500 001 1172207
003 DE-He213
005 20251202161851.0
006 m d
007 cr nn 008maaau
008 260625s2025 sz s 0 eng d
020 $a 9783031890222 $q (electronic bk.)
020 $a 9783031890215 $q (paper)
024 7 $a 10.1007/978-3-031-89022-2 $2 doi
035 $a 978-3-031-89022-2
040 $a GP $c GP
041 0 $a eng
050 4 $a Q335 $b .L46 2025
072 7 $a UYQ $2 bicssc
072 7 $a COM004000 $2 bisacsh
072 7 $a UYQ $2 thema
082 0 4 $a 006.3 $2 23
090 $a Q335 $b .L578 2025
100 1 $a Leofante, Francesco. $3 1502960
245 1 0 $a Robust explainable AI $h [electronic resource] / $c by Francesco Leofante, Matthew Wicker.
260 $a Cham : $c 2025. $b Springer Nature Switzerland : $b Imprint: Springer,
300 $a xii, 71 p. : $b ill. (some col.), digital ; $c 24 cm.
490 1 $a SpringerBriefs in intelligent systems. Artificial intelligence, multiagent systems, and cognitive robotics, $x 2196-5498
505 0 $a Foreword -- Preface -- Acknowledgements -- 1. Introduction -- 2. Explainability in Machine Learning: Preliminaries & Overview -- 3. Robustness of Counterfactual Explanations -- 4. Robustness of Saliency-Based Explanations.
520 $a The area of Explainable Artificial Intelligence (XAI) is concerned with providing methods and tools to improve the interpretability of black-box learning models. While several approaches exist to generate explanations, they are often lacking robustness, e.g., they may produce completely different explanations for similar events. This phenomenon has troubling implications, as lack of robustness indicates that explanations are not capturing the underlying decision-making process of a model and thus cannot be trusted. This book aims at introducing Robust Explainable AI, a rapidly growing field whose focus is to ensure that explanations for machine learning models adhere to the highest robustness standards. We will introduce the most important concepts, methodologies, and results in the field, with a particular focus on techniques developed for feature attribution methods and counterfactual explanations for deep neural networks. As prerequisites, a certain familiarity with neural networks and approaches within XAI is desirable but not mandatory. The book is designed to be self-contained, and relevant concepts will be introduced when needed, together with examples to ensure a successful learning experience.
650 0 $a Artificial intelligence. $3 559380
650 0 $a Machine learning. $3 561253
650 1 4 $a Artificial Intelligence. $3 646849
650 2 4 $a Machine Learning. $3 1137723
650 2 4 $a Knowledge Based Systems. $3 1365951
650 2 4 $a Privacy. $3 575491
650 2 4 $a Statistical Learning. $3 1396099
700 1 $a Wicker, Matthew. $3 1502961
710 2 $a SpringerLink (Online service) $3 593884
773 0 $t Springer Nature eBook
830 0 $a SpringerBriefs in intelligent systems. $p Artificial intelligence, multiagent systems, and cognitive robotics. $3 1109996
856 4 0 $u https://doi.org/10.1007/978-3-031-89022-2
950 $a Artificial Intelligence (R0) (SpringerNature-85269)