Human-Like Machine Intelligence最新文献

筛选
英文 中文
Modelling Virtual Bargaining using Logical Representation Change 基于逻辑表示变化的虚拟议价建模
Human-Like Machine Intelligence Pub Date : 2021-07-13 DOI: 10.1093/oso/9780198862536.003.0004
Allen Bundy, Eugene Philalithis, Xue Li
{"title":"Modelling Virtual Bargaining using Logical Representation Change","authors":"Allen Bundy, Eugene Philalithis, Xue Li","doi":"10.1093/oso/9780198862536.003.0004","DOIUrl":"https://doi.org/10.1093/oso/9780198862536.003.0004","url":null,"abstract":"We discuss work in progress on the computational modelling of virtual bargaining: inference-driven human coordination under severe communicative constraints. For this initial work we model variants of a two-player coordination game of item selection and avoidance taken from the current virtual bargaining literature. In this range of games, human participants collaborate to select items (e.g. bananas) or avoid items (e.g. scorpions), based on signalling conventions constructed and updated from shared assumptions, with minimal information exchange. We model behaviours in these games using logic programs interpretable as logical theories. From an initial theory comprised of rules, background assumptions and a basic signalling convention, we use automated theory repair to jointly adapt that basic signalling convention to novel contexts, with no explicit coordination between players. Our ABC system for theory repair delivers spontaneous adaptation, using reasoning failures to replace established conventions with better alternatives, matching human players’ own reasoning across several games.","PeriodicalId":423264,"journal":{"name":"Human-Like Machine Intelligence","volume":"35 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-07-13","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"125039297","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
引用次数: 5
Explanation in AI systems AI系统中的解释
Human-Like Machine Intelligence Pub Date : 2021-07-13 DOI: 10.1093/oso/9780198862536.003.0006
Marko Tešić, U. Hahn
{"title":"Explanation in AI systems","authors":"Marko Tešić, U. Hahn","doi":"10.1093/oso/9780198862536.003.0006","DOIUrl":"https://doi.org/10.1093/oso/9780198862536.003.0006","url":null,"abstract":"As AI systems come to permeate human society, there is an increasing need for such systems to explain their actions, conclusions, or decisions. This is presently fuelling a surge in interest in machine-generated explanation in the field of explainable AI. In this chapter, we examine work on explanations in areas ranging from AI to philosophy, psychology, and cognitive science. We point to different notions of explanation that are at play in these areas. We further discuss the theoretical work in philosophy and psychology on (good) explanation and its implications for the research on machine-generated explanations. Lastly, we consider the pragmatic nature of explanations and showcase its importance in the context of trust and fidelity. Throughout the chapter we suggest paths for further research on explanation in AI, psychology, philosophy, and cognitive science.","PeriodicalId":423264,"journal":{"name":"Human-Like Machine Intelligence","volume":"19 3","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-07-13","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"133043076","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
引用次数: 2
Human-Machine Perception of Complex Signal Data 复杂信号数据的人机感知
Human-Like Machine Intelligence Pub Date : 2021-07-13 DOI: 10.1093/oso/9780198862536.003.0012
Alaa Y. Alahmadi, Alan Davies, Markel Vigo, Katherine Dempsey, C. Jay
{"title":"Human-Machine Perception of Complex Signal Data","authors":"Alaa Y. Alahmadi, Alan Davies, Markel Vigo, Katherine Dempsey, C. Jay","doi":"10.1093/oso/9780198862536.003.0012","DOIUrl":"https://doi.org/10.1093/oso/9780198862536.003.0012","url":null,"abstract":"Electrocardiograms (ECGs), which capture the electrical activity of the human heart, are widely used in clinical practice, and notoriously difficult to interpret. Whilst there have been attempts to automate their interpretation for several decades, human reading of the data presented visually remains the ‘gold standard’. We demonstrate how a visualisation technique that significantly improves human interpretation of ECG data can be used as a basis for an automated interpretation algorithm that is more accurate than current signal processing techniques, and has the benefit of the human and machine sharing the same representation of the data. We discuss the potential of the approach, in terms of its accuracy and acceptability in clinical practice.","PeriodicalId":423264,"journal":{"name":"Human-Like Machine Intelligence","volume":"43 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-07-13","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"129586337","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
引用次数: 1
Spontaneous Communicative Conventions through Virtual Bargaining 虚拟议价中的自发交际惯例
Human-Like Machine Intelligence Pub Date : 2021-07-13 DOI: 10.1093/oso/9780198862536.003.0003
N. Chater, Jennifer Misyak
{"title":"Spontaneous Communicative Conventions through Virtual Bargaining","authors":"N. Chater, Jennifer Misyak","doi":"10.1093/oso/9780198862536.003.0003","DOIUrl":"https://doi.org/10.1093/oso/9780198862536.003.0003","url":null,"abstract":"Human-like computing will require machines to communicate interactively with people, to take in human knowledge and preferences, to explain the machine’s actions, and to generally coordinate human and machine behaviour. But even the simplest communicative interactions raise deep theoretical challenges. Human and machine spontaneously have to “agree” on the mapping between possible signals and messages. Such mappings are extremely flexible and influenced by large numbers of contextual factors in real-world interactions. Typically, there are many candidate signal-message mappings. Successful communication requires that both parties agree on the same mapping. We outline experimental and theoretical work exploring an approach to these problems based on “virtual bargaining,” according to which each communicative party attempts to infer which mapping would be agreed were prior communication possible. This chapter explores how such problems are solved by humans, and suggests directions for building computational models of these processes.","PeriodicalId":423264,"journal":{"name":"Human-Like Machine Intelligence","volume":"55 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-07-13","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"123328033","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
引用次数: 4
Human-like Communication 类人沟通
Human-Like Machine Intelligence Pub Date : 2021-07-13 DOI: 10.1093/oso/9780198862536.003.0007
P. Healey
{"title":"Human-like Communication","authors":"P. Healey","doi":"10.1093/oso/9780198862536.003.0007","DOIUrl":"https://doi.org/10.1093/oso/9780198862536.003.0007","url":null,"abstract":"The most famous grand challenge for machine intelligence is human-like communication. This chapter explores two problem that need to be solved in order for machines to meet this challenge. The first is the technical difficulties posed by ordinary conversation. Production and comprehension in conversation are: multimodal, multi-person, incremental, concurrent, and jointly managed. The fine-grained complexity of these aspects of human interaction are beyond the current state of the art but should, ultimately, be tractable. The second set of problems are foundational. Models that assume human communication is underwritten by a shared language are unable to account for the ubiuquitous and systematic role misunderstanding plays in everyday interaction. As a result they also fail to explain how people adapt their language use to each new person and new situation in real time. This capability is essential for any machine that aims to engage constructively with human diversity.","PeriodicalId":423264,"journal":{"name":"Human-Like Machine Intelligence","volume":"99 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-07-13","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"132073040","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
引用次数: 6
The Shared-Workspace Framework for Dialogue and Other Cooperative Joint Activities 对话和其他合作活动共享工作空间框架
Human-Like Machine Intelligence Pub Date : 2021-07-13 DOI: 10.1093/oso/9780198862536.003.0013
M. Pickering, S. Garrod
{"title":"The Shared-Workspace Framework for Dialogue and Other Cooperative Joint Activities","authors":"M. Pickering, S. Garrod","doi":"10.1093/oso/9780198862536.003.0013","DOIUrl":"https://doi.org/10.1093/oso/9780198862536.003.0013","url":null,"abstract":"We present a theory of dialogue as a form of cooperative joint activity. Dialogue is treated as a system involving two interlocutors and a shared workspace that contains their contributions and relevant non-linguistic context. The interlocutors construct shared plans and use them to “post” contributions to the workspace, to comprehend joint contributions, and to distribute control of the dialogue between them. A fundamental part of this process is to simulate their partner’s contributions and to use it to predict the upcoming state of the shared workspace. As a consequence, they align their linguistic representations and their representations of the situation and of the “games” underlying successful communication. The shared workspace is a highly limited resource, and the interlocutors use their aligned representations to say just enough and to speak in good time. We describe how dialogue and cooperative joint activity can be brought together in situated communication, and then sketch some implications of our account for human-like artificial systems.","PeriodicalId":423264,"journal":{"name":"Human-Like Machine Intelligence","volume":"29 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-07-13","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"116033274","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
引用次数: 1
Sampling as the Human Approximation to Probabilistic Inference 抽样作为人类对概率推理的近似
Human-Like Machine Intelligence Pub Date : 2021-07-13 DOI: 10.1093/oso/9780198862536.003.0021
Adam N. Sanborn, Jian-Qiao Zhu, Jake Spicer, Joakim Sundh, Pablo León-Villagrá, N. Chater
{"title":"Sampling as the Human Approximation to Probabilistic Inference","authors":"Adam N. Sanborn, Jian-Qiao Zhu, Jake Spicer, Joakim Sundh, Pablo León-Villagrá, N. Chater","doi":"10.1093/oso/9780198862536.003.0021","DOIUrl":"https://doi.org/10.1093/oso/9780198862536.003.0021","url":null,"abstract":"Human beings perform well in uncertain environments, matching the performance of complex probabilistic models in complex tasks such as language or physical system prediction. Yet people’s judgments about probabilities also display well-known biases. How can this be? Recently cognitive scientists have explored the possibility that the same sampling algorithms that are used in computer science to approximate complex probabilistic models are also used in the mind and the brain. We the review experimental evidence that characterises the human sampling algorithm, and discuss how such an algorithm could potentially explain apects of the movement of asset prices in financial markets. We also discuss how many of the biases that people display may be the direct result of using only a small number of samples, but using them efficiently. As human beings make successful real-time decisions using only rough estimates of uncertainty, this suggests that machine intelligence could do the same.","PeriodicalId":423264,"journal":{"name":"Human-Like Machine Intelligence","volume":"20 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-07-13","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"125143134","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
引用次数: 2
Mining Property-driven Graphical Explanations for Data-centric AI from Argumentation Frameworks 从论证框架为以数据为中心的人工智能挖掘属性驱动的图形解释
Human-Like Machine Intelligence Pub Date : 2021-07-13 DOI: 10.1093/oso/9780198862536.003.0005
O. Cocarascu, K. Čyras, Antonio Rago, Francesca Toni
{"title":"Mining Property-driven Graphical Explanations for Data-centric AI from Argumentation Frameworks","authors":"O. Cocarascu, K. Čyras, Antonio Rago, Francesca Toni","doi":"10.1093/oso/9780198862536.003.0005","DOIUrl":"https://doi.org/10.1093/oso/9780198862536.003.0005","url":null,"abstract":"Adoption of AI-equipped systems and their societal benefits are heavily dependent on human understanding of the rationale behind the systems’ outputs. Such systems’ widespread inability to explain their outputs causes human mistrust and doubts regarding their regulatory compliance. Research in psychology points to the amenability of argumentation as a paradigm for human reasoning, advocating that humans developed reasoning in order to argue. We here overview a number of approaches using computational argumentation frameworks as the scaffolding for explanations for human consumption. Our argumentation frameworks are automatically mined from data and data-centric methods. We define explanations as graphs obtained from these argumentation frameworks, which are customisable by means of properties. We illustrate our methods with various consumer-oriented tasks in the media and entertainment industry, providing reasoning outputs that can be explained to consumers, and that consumers can directly interact with to give rise to improved recommendations.","PeriodicalId":423264,"journal":{"name":"Human-Like Machine Intelligence","volume":"12 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-07-13","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"133185813","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
引用次数: 0
Automated Common-sense Spatial Reasoning: Still a Huge Challenge 自动常识空间推理:仍然是一个巨大的挑战
Human-Like Machine Intelligence Pub Date : 2021-07-13 DOI: 10.1093/oso/9780198862536.003.0020
B. Bennett, A. Cohn
{"title":"Automated Common-sense Spatial Reasoning: Still a Huge Challenge","authors":"B. Bennett, A. Cohn","doi":"10.1093/oso/9780198862536.003.0020","DOIUrl":"https://doi.org/10.1093/oso/9780198862536.003.0020","url":null,"abstract":"Achieving “commonsense reasoning” capabilities has been one of the goals of AI since its inception. However, as Marcus and Davis have recently argued, “Common sense is not just the hardest problem for AI; in the long run, it’s also the most important problem”. Moreover, it is generally accepted that space (and time) underlie much of what we regard as commonsense reasoning. Despite many successes in dealing with particular restricted types of spatial information, the development of a system capable of carrying out automated spatial reasoning of similar diversity to what one finds in ordinary natural language descriptions, seems to be a long way off. The chapter gives a general (though not comprehensive) overview of the goal of automating commonsense spatial reasoning by means of symbolic representations and reasoning. Existing work is surveyed, the nature of the goal clarified, and the problem analysed into seven interacting sub-problems.","PeriodicalId":423264,"journal":{"name":"Human-Like Machine Intelligence","volume":"75 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-07-13","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"126809961","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
引用次数: 3
Interactive Learning with Mutual Explanations in Relational Domains 关系领域中相互解释的交互式学习
Human-Like Machine Intelligence Pub Date : 2021-07-13 DOI: 10.1093/oso/9780198862536.003.0017
Ute Schmid
{"title":"Interactive Learning with Mutual Explanations in Relational Domains","authors":"Ute Schmid","doi":"10.1093/oso/9780198862536.003.0017","DOIUrl":"https://doi.org/10.1093/oso/9780198862536.003.0017","url":null,"abstract":"With the growing number of applications of machine learning in complex real-world domains machine learning research has to meet new requirements to deal with the imperfections of real world data and the legal as well as ethical obligations to make classifier decisions transparent and comprehensible. In this contribution, arguments for interpretable and interactive approaches to machine learning are presented. It is argued that visual explanations are often not expressive enough to grasp critical information which relies on relations between different aspects or sub-concepts. Consequently, inductive logic programming (ILP) and the generation of verbal explanations from Prolog rules is advocated. Interactive learning in the context of ILP is illustrated with the Dare2Del system which helps users to manage their digital clutter. It is shown that verbal explanations overcome the explanatory one-way street from AI system to user. Interactive learning with mutual explanations allows the learning system to take into account not only class corrections but also corrections of explanations to guide learning. We propose mutual explanations as a building-block for human-like computing and an important ingredient for human AI partnership.","PeriodicalId":423264,"journal":{"name":"Human-Like Machine Intelligence","volume":"12 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-07-13","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"125177196","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
引用次数: 7
0
×
引用
GB/T 7714-2015
复制
MLA
复制
APA
复制
导出至
BibTeX EndNote RefMan NoteFirst NoteExpress
×
提示
您的信息不完整,为了账户安全,请先补充。
现在去补充
×
提示
您因"违规操作"
具体请查看互助需知
我知道了
×
提示
确定
请完成安全验证×
相关产品
×
本文献相关产品
联系我们:info@booksci.cn Book学术提供免费学术资源搜索服务,方便国内外学者检索中英文文献。致力于提供最便捷和优质的服务体验。 Copyright © 2023 布克学术 All rights reserved.
京ICP备2023020795号-1
ghs 京公网安备 11010802042870号
Book学术文献互助
Book学术文献互助群
群 号:604180095
Book学术官方微信
小红书