05035nam a22006135i 4500 978-3-031-69974-0 DE-He213 20251030114629.0 cr nn 008mamaa 241220s2024 sz | s |||| 0|eng d 9783031699740 978-3-031-69974-0 10.1007/978-3-031-69974-0 doi Q334-342 TA347.A78 UYQ bicssc COM004000 bisacsh UYQ thema Ilievski, Filip. author. aut http://id.loc.gov/vocabulary/relators/aut 89236 Human-Centric AI with Common Sense [electronic resource] / by Filip Ilievski. 1st ed. 2024. Cham : Springer Nature Switzerland : Imprint: Springer, 2024. XV, 137 p. 30 illus., 27 illus. in color. online resource. text txt rdacontent computer c rdamedia online resource cr rdacarrier text file PDF rda Synthesis Lectures on Computer Science, 1932-1686 Introduction -- Collaborative Commonsense Reasoning -- Adaptive Commonsense Reasoning -- Responsible Commonsense Reasoning -- Explainable Commonsense Reasoning -- Hybrid Intelligence with Common Sense -- Conclusions and Outlook. This book enables readers to understand the challenges and opportunities of developing human-centered AI with commonsense reasoning abilities. Despite apparent accuracy improvements brought by large neural models across task benchmarks, common sense is still lacking. The lack of common sense affects many tasks, including story understanding, decision-making, and question answering. Commonsense knowledge and reasoning have long been considered the “black matter” of AI, raising concerns about the trustworthiness and applicability of AI methods in both autonomous and hybrid applications. This book describes how to design a more robust, collaborative, explainable, and responsible AI through incorporating neuro-symbolic commonsense reasoning. In addition, the book provides examples of how these properties of AI can facilitate a wide range of social-good applications in digital democracy, traffic monitoring, education, and robotics. What makes commonsense reasoning such a unique and impactful challenge? What can we learn from cognitive research when designing and developing AI systems? How can we approach building responsible, robust, collaborative, and explainable AI with common sense? And finally, what is the impact of this work on human-AI teaming? This book provides an accessible introduction and exploration of these topics. In addition, this book: Features cognitive, symbolic, and neural theories and methods for commonsense reasoning Integrates neural and symbolic methods for open-domain tasks built on robustness, adaptivity, collaboration, and responsibility principles Synthesizes lessons learned and provides open challenges that future research and engineering efforts need to tackle About the Author Filip Ilievski, Ph.D., is a Senior Assistant Professor of Commonsense AI at the Vrije Universiteit (VU) Amsterdam’s Computer Science department. Dr. Ilievski is an affiliated scientist at the USC Information Sciences Institute (ISI), where he was previously a Research Lead and played a key role in a team within the DARPA Machine Common Sense (MCS) program. Dr. Ilievski holds a Ph.D. in Natural Language Processing. His research focuses on developing robust and explainable neuro-symbolic technology with positive real-world impact, based on neural methods and high-quality knowledge. Dr. Ilievski has also made extensive contributions in identifying long-tail entities in text, interpretation of internet memes, and enabling access to large-scale knowledge resources. Artificial intelligence. 58441 Natural language processing (Computer science). 65131 Reasoning. 76426 Computer science. 58552 User interfaces (Computer systems). 64688 Human-computer interaction. 64854 Application software. Artificial Intelligence. 58441 Natural Language Processing (NLP). 66164 Formal Reasoning. 77299 Computer Science. 58552 User Interfaces and Human Computer Interaction. 66577 Computer and Information Systems Applications. SpringerLink (Online service) Springer Nature eBook Printed edition: 9783031699733 Printed edition: 9783031699757 Printed edition: 9783031699764 Synthesis Lectures on Computer Science, 1932-1686 65520 https://doi.org/10.1007/978-3-031-69974-0 ZDB-2-SXSC 65875 65875