國立虎尾科技大學 |

xxAI - Beyond Explainable AI = International Workshop, Held in Conjunction with ICML 2020, July 18, 2020, Vienna, Austria, Revised and Extended Papers /

紀錄類型:	書目-語言資料,印刷品 : Monograph/item
正題名/作者:	xxAI - Beyond Explainable AI/ edited by Andreas Holzinger, Randy Goebel, Ruth Fong, Taesup Moon, Klaus-Robert Müller, Wojciech Samek.
其他題名:	International Workshop, Held in Conjunction with ICML 2020, July 18, 2020, Vienna, Austria, Revised and Extended Papers /
其他作者:	Samek, Wojciech.
面頁冊數:	X, 397 p. 124 illus., 114 illus. in color.online resource. :
Contained By:	Springer Nature eBook
標題:	Machine Learning. -
電子資源:	https://doi.org/10.1007/978-3-031-04083-2
ISBN:	9783031040832

xxAI - Beyond Explainable AI = International Workshop, Held in Conjunction with ICML 2020, July 18, 2020, Vienna, Austria, Revised and Extended Papers /
xxAI - Beyond Explainable AIInternational Workshop, Held in Conjunction with ICML 2020, July 18, 2020, Vienna, Austria, Revised and Extended Papers /[electronic resource] :edited by Andreas Holzinger, Randy Goebel, Ruth Fong, Taesup Moon, Klaus-Robert Müller, Wojciech Samek. - 1st ed. 2022. - X, 397 p. 124 illus., 114 illus. in color.online resource. - Lecture Notes in Artificial Intelligence,132002945-9141 ;. - Lecture Notes in Artificial Intelligence,13406.

Editorial -- xxAI - Beyond explainable Artificial Intelligence -- Current Methods and Challenges -- Explainable AI Methods - A Brief Overview -- Challenges in Deploying Explainable Machine Learning -- Methods for Machine Learning Models -- CLEVR-X: A Visual Reasoning Dataset for Natural Language Explanations -- New Developments in Explainable AI -- A Rate-Distortion Framework for Explaining Black-box Model Decisions -- Explaining the Predictions of Unsupervised Learning Models -- Towards Causal Algorithmic Recourse -- Interpreting Generative Adversarial Networks for Interactive Image Generation -- XAI and Strategy Extraction via Reward Redistribution -- Interpretable, Verifiable, and Robust Reinforcement Learning via Program Synthesis -- Interpreting and improving deep-learning models with reality checks -- Beyond the Visual Analysis of Deep Model Saliency -- ECQ^2: Quantization for Low-Bit and Sparse DNNs -- A whale’s tail - Finding the right whale in an uncertain world -- Explainable Artificial Intelligence in Meteorology and Climate Science: Model fine-tuning, calibrating trust and learning new science -- An Interdisciplinary Approach to Explainable AI.-Varieties of AI Explanations under the Law - From the GDPR to the AIA, and beyond -- Towards Explainability for AI Fairness -- Logic and Pragmatics in AI Explanation.

Open Access

This is an open access book. Statistical machine learning (ML) has triggered a renaissance of artificial intelligence (AI). While the most successful ML models, including Deep Neural Networks (DNN), have developed better predictivity, they have become increasingly complex, at the expense of human interpretability (correlation vs. causality). The field of explainable AI (xAI) has emerged with the goal of creating tools and models that are both predictive and interpretable and understandable for humans. Explainable AI is receiving huge interest in the machine learning and AI research communities, across academia, industry, and government, and there is now an excellent opportunity to push towards successful explainable AI applications. This volume will help the research community to accelerate this process, to promote a more systematic use of explainable AI to improve models in diverse applications, and ultimately to better understand how current explainable AI methods need to be improved and what kind of theory of explainable AI is needed. After overviews of current methods and challenges, the editors include chapters that describe new developments in explainable AI. The contributions are from leading researchers in the field, drawn from both academia and industry, and many of the chapters take a clear interdisciplinary approach to problem-solving. The concepts discussed include explainability, causability, and AI interfaces with humans, and the applications include image processing, natural language, law, fairness, and climate science.

ISBN: 9783031040832

Standard No.: 10.1007/978-3-031-04083-2doiSubjects--Topical Terms:

1137723
Machine Learning.

LC Class. No.: Q334-342

Dewey Class. No.: 006.3

xxAI - Beyond Explainable AI = International Workshop, Held in Conjunction with ICML 2020, July 18, 2020, Vienna, Austria, Revised and Extended Papers /
LDR:04563nam a22004455i 4500 001 1092847
003 DE-He213
005 20221012210541.0
007 cr nn 008mamaa
008 221228s2022 sz | s |||| 0|eng d
020 $a 9783031040832 $9 978-3-031-04083-2
024 7 $a 10.1007/978-3-031-04083-2 $2 doi
035 $a 978-3-031-04083-2
050 4 $a Q334-342
050 4 $a TA347.A78
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
245 1 0 $a xxAI - Beyond Explainable AI $h [electronic resource] : $b International Workshop, Held in Conjunction with ICML 2020, July 18, 2020, Vienna, Austria, Revised and Extended Papers / $c edited by Andreas Holzinger, Randy Goebel, Ruth Fong, Taesup Moon, Klaus-Robert Müller, Wojciech Samek.
250 $a 1st ed. 2022.
264 1 $a Cham : $b Springer International Publishing : $b Imprint: Springer, $c 2022.
300 $a X, 397 p. 124 illus., 114 illus. in color. $b online resource.
336 $a text $b txt $2 rdacontent
337 $a computer $b c $2 rdamedia
338 $a online resource $b cr $2 rdacarrier
347 $a text file $b PDF $2 rda
490 1 $a Lecture Notes in Artificial Intelligence, $x 2945-9141 ; $v 13200
505 0 $a Editorial -- xxAI - Beyond explainable Artificial Intelligence -- Current Methods and Challenges -- Explainable AI Methods - A Brief Overview -- Challenges in Deploying Explainable Machine Learning -- Methods for Machine Learning Models -- CLEVR-X: A Visual Reasoning Dataset for Natural Language Explanations -- New Developments in Explainable AI -- A Rate-Distortion Framework for Explaining Black-box Model Decisions -- Explaining the Predictions of Unsupervised Learning Models -- Towards Causal Algorithmic Recourse -- Interpreting Generative Adversarial Networks for Interactive Image Generation -- XAI and Strategy Extraction via Reward Redistribution -- Interpretable, Verifiable, and Robust Reinforcement Learning via Program Synthesis -- Interpreting and improving deep-learning models with reality checks -- Beyond the Visual Analysis of Deep Model Saliency -- ECQ^2: Quantization for Low-Bit and Sparse DNNs -- A whale’s tail - Finding the right whale in an uncertain world -- Explainable Artificial Intelligence in Meteorology and Climate Science: Model fine-tuning, calibrating trust and learning new science -- An Interdisciplinary Approach to Explainable AI.-Varieties of AI Explanations under the Law - From the GDPR to the AIA, and beyond -- Towards Explainability for AI Fairness -- Logic and Pragmatics in AI Explanation.
506 0 $a Open Access
520 $a This is an open access book. Statistical machine learning (ML) has triggered a renaissance of artificial intelligence (AI). While the most successful ML models, including Deep Neural Networks (DNN), have developed better predictivity, they have become increasingly complex, at the expense of human interpretability (correlation vs. causality). The field of explainable AI (xAI) has emerged with the goal of creating tools and models that are both predictive and interpretable and understandable for humans. Explainable AI is receiving huge interest in the machine learning and AI research communities, across academia, industry, and government, and there is now an excellent opportunity to push towards successful explainable AI applications. This volume will help the research community to accelerate this process, to promote a more systematic use of explainable AI to improve models in diverse applications, and ultimately to better understand how current explainable AI methods need to be improved and what kind of theory of explainable AI is needed. After overviews of current methods and challenges, the editors include chapters that describe new developments in explainable AI. The contributions are from leading researchers in the field, drawn from both academia and industry, and many of the chapters take a clear interdisciplinary approach to problem-solving. The concepts discussed include explainability, causability, and AI interfaces with humans, and the applications include image processing, natural language, law, fairness, and climate science.
650 2 4 $a Machine Learning. $3 1137723
650 1 4 $a Artificial Intelligence. $3 646849
650 0 $a Machine learning. $3 561253
650 0 $a Artificial intelligence. $3 559380
700 1 $a Samek, Wojciech. $e editor. $1 https://orcid.org/0000-0002-6283-3265 $4 edt $4 http://id.loc.gov/vocabulary/relators/edt $3 1305121
700 1 $a Müller, Klaus-Robert. $e editor. $1 https://orcid.org/0000-0002-3861-7685 $4 edt $4 http://id.loc.gov/vocabulary/relators/edt $3 1261634
700 1 $a Moon, Taesup. $e editor. $4 edt $4 http://id.loc.gov/vocabulary/relators/edt $3 1400682
700 1 $a Fong, Ruth. $e editor. $4 edt $4 http://id.loc.gov/vocabulary/relators/edt $3 1400681
700 1 $a Goebel, Randy. $e editor. $4 edt $4 http://id.loc.gov/vocabulary/relators/edt $3 1325406
700 1 $a Holzinger, Andreas. $4 edt $4 http://id.loc.gov/vocabulary/relators/edt $3 792501
710 2 $a SpringerLink (Online service) $3 593884
773 0 $t Springer Nature eBook
776 0 8 $i Printed edition: $z 9783031040825
776 0 8 $i Printed edition: $z 9783031040849
830 0 $a Lecture Notes in Artificial Intelligence, $x 2945-9141 ; $v 13406 $3 1387736
856 4 0 $u https://doi.org/10.1007/978-3-031-04083-2
912 $a ZDB-2-SCS
912 $a ZDB-2-SXCS
912 $a ZDB-2-LNC
912 $a ZDB-2-SOB
950 $a Computer Science (SpringerNature-11645)
950 $a Computer Science (R0) (SpringerNature-43710)