xxAI - Beyond Explainable AI

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 in...

وصف كامل

محفوظ في:
التفاصيل البيبلوغرافية
التنسيق: Online
اللغة:الإنجليزية
منشور في: Springer Nature 2022
الموضوعات:
الوصول للمادة أونلاين:ONIX_20220513_9783031040832_35
الوسوم: إضافة وسم
لا توجد وسوم, كن أول من يضع وسما على هذه التسجيلة!
_version_ 1869515216606199808
collection Directory of Open Access Books
description 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.
format Online
id doab-20.500.12854ir-81682
institution Directory of Open Access Books
language eng
publishDate 2022
publishDateRange 2022
publishDateSort 2022
publisher Springer Nature
publisherStr Springer Nature
record_format ojs
spelling doab-20.500.12854ir-816822025-03-16T06:26:33Z xxAI - Beyond Explainable AI Holzinger, Andreas Goebel, Randy Fong, Ruth Moon, Taesup Müller, Klaus-Robert Samek, Wojciech Computer Science Informatics Conference Proceedings Research Applications 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. 2022-05-14T04:03:03Z 2022-05-14T04:03:03Z 2022-05-13T12:19:29Z 2022 book ONIX_20220513_9783031040832_35 OCN: 1311285955 https://library.oapen.org/handle/20.500.12657/54443 9783031040832 https://directory.doabooks.org/handle/20.500.12854/81682 eng Lecture Notes in Computer Science; Lecture Notes in Artificial Intelligence open access image/jpeg image/jpeg image/jpeg n/a n/a n/a https://library.oapen.org/bitstream/20.500.12657/54443/1/978-3-031-04083-2.pdf https://library.oapen.org/bitstream/20.500.12657/54443/1/978-3-031-04083-2.pdf https://library.oapen.org/bitstream/20.500.12657/54443/1/978-3-031-04083-2.pdf Springer Nature Springer International Publishing 10.1007/978-3-031-04083-2 10.1007/978-3-031-04083-2 9fa3421d-f917-4153-b9ab-fc337c396b5a 9783031040832 Springer International Publishing 397 Cham open access
spellingShingle Computer Science
Informatics
Conference Proceedings
Research
Applications
xxAI - Beyond Explainable AI
title xxAI - Beyond Explainable AI
title_full xxAI - Beyond Explainable AI
title_fullStr xxAI - Beyond Explainable AI
title_full_unstemmed xxAI - Beyond Explainable AI
title_short xxAI - Beyond Explainable AI
title_sort xxai beyond explainable ai
topic Computer Science
Informatics
Conference Proceedings
Research
Applications
topic_facet Computer Science
Informatics
Conference Proceedings
Research
Applications
url ONIX_20220513_9783031040832_35