Pub Date : 2022-04-16DOI: 10.1007/s11023-022-09601-1
M. Green, Jan G. Michel
{"title":"Correction to: What Might Machines Mean?","authors":"M. Green, Jan G. Michel","doi":"10.1007/s11023-022-09601-1","DOIUrl":"https://doi.org/10.1007/s11023-022-09601-1","url":null,"abstract":"","PeriodicalId":51133,"journal":{"name":"Minds and Machines","volume":null,"pages":null},"PeriodicalIF":7.4,"publicationDate":"2022-04-16","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"46511586","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2022-03-16DOI: 10.1007/s11023-022-09598-7
David S. Watson, Limor Gultchin, Ankur Taly, Luciano Floridi
Necessity and sufficiency are the building blocks of all successful explanations. Yet despite their importance, these notions have been conceptually underdeveloped and inconsistently applied in explainable artificial intelligence (XAI), a fast-growing research area that is so far lacking in firm theoretical foundations. In this article, an expanded version of a paper originally presented at the 37th Conference on Uncertainty in Artificial Intelligence (Watson et al., 2021), we attempt to fill this gap. Building on work in logic, probability, and causality, we establish the central role of necessity and sufficiency in XAI, unifying seemingly disparate methods in a single formal framework. We propose a novel formulation of these concepts, and demonstrate its advantages over leading alternatives. We present a sound and complete algorithm for computing explanatory factors with respect to a given context and set of agentive preferences, allowing users to identify necessary and sufficient conditions for desired outcomes at minimal cost. Experiments on real and simulated data confirm our method’s competitive performance against state of the art XAI tools on a diverse array of tasks.
必要性和充分性是所有成功解释的基石。然而，尽管这些概念很重要，但它们在概念上并不发达，在可解释人工智能(XAI)中的应用也不一致。可解释人工智能是一个快速发展的研究领域，迄今为止还缺乏坚实的理论基础。本文是第37届人工智能不确定性会议(Watson et al.， 2021)上发表的一篇论文的扩展版，我们试图填补这一空白。在逻辑、概率和因果关系的基础上，我们在XAI中建立了必要性和充分性的中心角色，将看似不同的方法统一在一个形式框架中。我们提出了这些概念的新公式，并展示了其优于领先替代方案的优势。我们提出了一种可靠而完整的算法，用于计算给定上下文和一组代理偏好的解释因素，允许用户以最小的成本识别期望结果的必要和充分条件。在真实和模拟数据上的实验证实，我们的方法在各种任务上与最先进的XAI工具相比具有竞争力。
{"title":"Local Explanations via Necessity and Sufficiency: Unifying Theory and Practice","authors":"David S. Watson, Limor Gultchin, Ankur Taly, Luciano Floridi","doi":"10.1007/s11023-022-09598-7","DOIUrl":"https://doi.org/10.1007/s11023-022-09598-7","url":null,"abstract":"<p>Necessity and sufficiency are the building blocks of all successful explanations. Yet despite their importance, these notions have been conceptually underdeveloped and inconsistently applied in explainable artificial intelligence (XAI), a fast-growing research area that is so far lacking in firm theoretical foundations. In this article, an expanded version of a paper originally presented at the 37th Conference on Uncertainty in Artificial Intelligence (Watson et al., 2021), we attempt to fill this gap. Building on work in logic, probability, and causality, we establish the central role of necessity and sufficiency in XAI, unifying seemingly disparate methods in a single formal framework. We propose a novel formulation of these concepts, and demonstrate its advantages over leading alternatives. We present a sound and complete algorithm for computing explanatory factors with respect to a given context and set of agentive preferences, allowing users to identify necessary and sufficient conditions for desired outcomes at minimal cost. Experiments on real and simulated data confirm our method’s competitive performance against state of the art XAI tools on a diverse array of tasks.</p>","PeriodicalId":51133,"journal":{"name":"Minds and Machines","volume":null,"pages":null},"PeriodicalIF":7.4,"publicationDate":"2022-03-16","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"138513212","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2022-03-07DOI: 10.1007/s11023-022-09593-y
Paula Sweeney
{"title":"Why Indirect Harms do not Support Social Robot Rights","authors":"Paula Sweeney","doi":"10.1007/s11023-022-09593-y","DOIUrl":"https://doi.org/10.1007/s11023-022-09593-y","url":null,"abstract":"","PeriodicalId":51133,"journal":{"name":"Minds and Machines","volume":null,"pages":null},"PeriodicalIF":7.4,"publicationDate":"2022-03-07","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"41707654","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2022-03-01DOI: 10.1007/s11023-022-09600-2
Gabe Dupre
{"title":"Correction to: (What) Can Deep Learning Contribute to Theoretical Linguistics?","authors":"Gabe Dupre","doi":"10.1007/s11023-022-09600-2","DOIUrl":"https://doi.org/10.1007/s11023-022-09600-2","url":null,"abstract":"","PeriodicalId":51133,"journal":{"name":"Minds and Machines","volume":null,"pages":null},"PeriodicalIF":7.4,"publicationDate":"2022-03-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"44886605","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2022-03-01DOI: 10.1007/s11023-022-09596-9
Hajo Greif
{"title":"Analogue Models and Universal Machines. Paradigms of Epistemic Transparency in Artificial Intelligence","authors":"Hajo Greif","doi":"10.1007/s11023-022-09596-9","DOIUrl":"https://doi.org/10.1007/s11023-022-09596-9","url":null,"abstract":"","PeriodicalId":51133,"journal":{"name":"Minds and Machines","volume":null,"pages":null},"PeriodicalIF":7.4,"publicationDate":"2022-03-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"52619954","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2022-03-01DOI: 10.1007/s11023-022-09597-8
F. J. Boge,P. Grünke,R. Hillerbrand
{"title":"Minds and Machines Special Issue: Machine Learning: Prediction Without Explanation?","authors":"F. J. Boge,P. Grünke,R. Hillerbrand","doi":"10.1007/s11023-022-09597-8","DOIUrl":"https://doi.org/10.1007/s11023-022-09597-8","url":null,"abstract":"","PeriodicalId":51133,"journal":{"name":"Minds and Machines","volume":null,"pages":null},"PeriodicalIF":7.4,"publicationDate":"2022-03-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"138513213","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2022-03-01DOI: 10.1007/s11023-022-09592-z
Falco J. Bargagli-Stoffi, G. Cevolani, G. Gnecco
{"title":"Simple Models in Complex Worlds: Occam’s Razor and Statistical Learning Theory","authors":"Falco J. Bargagli-Stoffi, G. Cevolani, G. Gnecco","doi":"10.1007/s11023-022-09592-z","DOIUrl":"https://doi.org/10.1007/s11023-022-09592-z","url":null,"abstract":"","PeriodicalId":51133,"journal":{"name":"Minds and Machines","volume":null,"pages":null},"PeriodicalIF":7.4,"publicationDate":"2022-03-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"44069927","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2022-03-01DOI: 10.1007/s11023-021-09583-6
Carlos A. Zednik, Hannes Boelsen
{"title":"Scientific Exploration and Explainable Artificial Intelligence","authors":"Carlos A. Zednik, Hannes Boelsen","doi":"10.1007/s11023-021-09583-6","DOIUrl":"https://doi.org/10.1007/s11023-021-09583-6","url":null,"abstract":"","PeriodicalId":51133,"journal":{"name":"Minds and Machines","volume":null,"pages":null},"PeriodicalIF":7.4,"publicationDate":"2022-03-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"52620398","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2022-02-25DOI: 10.1007/s11023-022-09595-w
Nina Poth
{"title":"Schema-Centred Unity and Process-Centred Pluralism of the Predictive Mind","authors":"Nina Poth","doi":"10.1007/s11023-022-09595-w","DOIUrl":"https://doi.org/10.1007/s11023-022-09595-w","url":null,"abstract":"","PeriodicalId":51133,"journal":{"name":"Minds and Machines","volume":null,"pages":null},"PeriodicalIF":7.4,"publicationDate":"2022-02-25","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"47686760","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
扫码关注我们
求助内容：
应助结果提醒方式：
京公网安备 11010802042870号