Relevant bibliographies by topics / Contrastive Explanations

Academic literature on the topic 'Contrastive Explanations'

Author: Grafiati
Published: 10 December 2022
Last updated: 29 January 2023

Create a spot-on reference in APA, MLA, Chicago, Harvard, and other styles

Select a source type:

Contents

Consult the lists of relevant articles, books, theses, conference reports, and other scholarly sources on the topic 'Contrastive Explanations.'

Next to every source in the list of references, there is an 'Add to bibliography' button. Press on it, and we will generate automatically the bibliographic reference to the chosen work in the citation style you need: APA, MLA, Harvard, Chicago, Vancouver, etc.

You can also download the full text of the academic publication as pdf and read online its abstract whenever available in the metadata.

Journal articles on the topic "Contrastive Explanations"

1

Morton, Adam. "Mathematical Modelling and Contrastive Explanation." Canadian Journal of Philosophy Supplementary Volume 16 (1990): 251–70. http://dx.doi.org/10.1080/00455091.1990.10717228.

Full text
Abstract:
This is an enquiry into flawed explanations. Most of the effort in studies of the concept of explanation, scientific or otherwise, has gone into the contrast between clear cases of explanation and clear non-explanations.
APA, Harvard, Vancouver, ISO, and other styles
2

Lipton, Peter. "Contrastive Explanation." Royal Institute of Philosophy Supplement 27 (March 1990): 247–66. http://dx.doi.org/10.1017/s1358246100005130.

Full text
Abstract:
According to a causal model of explanation, we explain phenomena by giving their causes or, where the phenomena are themselves causal regularities, we explain them by giving a mechanism linking cause and effect. If we explain why smoking causes cancer, we do not give the cause of this causal connection, but we do give the causal mechanism that makes it. The claim that to explain is to give a cause is not only natural and plausible, but it also avoids many of the objections to other accounts of explanation, such as the views that to explain is to give a reason to believe the phenomenon occurred, to somehow make the phenomenon familiar, or to give a Deductive-Nomological argument. Unlike the reason for belief account, a causal model makes a clear distinction between understanding why a phenomenon occurs and merely knowing that it does, and the model does so in a way that makes understanding unmysterious and objective. Understanding is not some sort of super-knowledge, but simply more knowledge: knowledge of the phenomenon and knowledge of its causal history. A causal model makes it clear how something can explain without itself being explained, and so avoids the regress of whys, since we can know a phenomenon's cause without knowing the cause of the cause. It also accounts for legitimate self-evidencing explanations, explanations where the phenomenon is an essential part of the evidence that the explanation is correct, so the explanation can not supply a non-circular reason for believing the phenomenon occurred. There is no barrier to knowing a cause through its effects and also knowing that it is their cause. The speed of recession of a star explains its observed red-shift, even though the shift is an essential part of the evidence for its speed of recession. The model also avoids the most serious objection to the familiarity view, which is that some phenomena are familiar yet not understood, since a phenomenon can be perfectly familiar, such as the blueness of the sky or the fact that the same side of the moon always faces the earth, even if we do not know its cause. Finally, a causal model avoids many of the objections to the Deductive-Nomological model. Ordinary explanations do not have to meet the requirements of the Deductive-Nomological model, because one does not need to give a law to give a cause, and one does not need to know a law to have good reason to believe that a cause is a cause. As for the notorious over-permissiveness of the Deductive-Nomological model, the reason recession explains red-shift but not conversely, is simply that causes explain effects but not conversely, and the reason a conjunction of laws does not explain its conjuncts is that conjunctions do not cause their conjuncts.
APA, Harvard, Vancouver, ISO, and other styles
3

Khalifa, Kareem. "Contrastive Explanations as Social Accounts." Social Epistemology 24, no. 4 (October 2010): 263–84. http://dx.doi.org/10.1080/02691728.2010.506960.

Full text
APA, Harvard, Vancouver, ISO, and other styles
4

Boulter, Stephen. "CONTRASTIVE EXPLANATIONS IN EVOLUTIONARY BIOLOGY." Ratio 25, no. 4 (November 6, 2012): 425–41. http://dx.doi.org/10.1111/j.1467-9329.2012.00555.x.

Full text
APA, Harvard, Vancouver, ISO, and other styles
5

Glymour, Bruce. "Contrastive, Non-Probabilistic Statistical Explanations." Philosophy of Science 65, no. 3 (September 1998): 448–71. http://dx.doi.org/10.1086/392656.

Full text
APA, Harvard, Vancouver, ISO, and other styles
6

Elzein, Nadine. "The demand for contrastive explanations." Philosophical Studies 176, no. 5 (February 22, 2018): 1325–39. http://dx.doi.org/10.1007/s11098-018-1065-z.

Full text
APA, Harvard, Vancouver, ISO, and other styles
7

Levy, Neil. "Contrastive Explanations: A Dilemma for Libertarians." Dialectica 59, no. 1 (July 1, 2005): 51–61. http://dx.doi.org/10.1111/j.1746-8361.2005.01004.x.

Full text
APA, Harvard, Vancouver, ISO, and other styles
8

Krarup, Benjamin, Senka Krivic, Daniele Magazzeni, Derek Long, Michael Cashmore, and David E. Smith. "Contrastive Explanations of Plans through Model Restrictions." Journal of Artificial Intelligence Research 72 (October 27, 2021): 533–612. http://dx.doi.org/10.1613/jair.1.12813.

Full text
Abstract:
In automated planning, the need for explanations arises when there is a mismatch between a proposed plan and the user’s expectation. We frame Explainable AI Planning as an iterative plan exploration process, in which the user asks a succession of contrastive questions that lead to the generation and solution of hypothetical planning problems that are restrictions of the original problem. The object of the exploration is for the user to understand the constraints that govern the original plan and, ultimately, to arrive at a satisfactory plan. We present the results of a user study that demonstrates that when users ask questions about plans, those questions are usually contrastive, i.e. “why A rather than B?”. We use the data from this study to construct a taxonomy of user questions that often arise during plan exploration. Our approach to iterative plan exploration is a process of successive model restriction. Each contrastive user question imposes a set of constraints on the planning problem, leading to the construction of a new hypothetical planning problem as a restriction of the original. Solving this restricted problem results in a plan that can be compared with the original plan, admitting a contrastive explanation. We formally define model-based compilations in PDDL2.1 for each type of constraint derived from a contrastive user question in the taxonomy, and empirically evaluate the compilations in terms of computational complexity. The compilations were implemented as part of an explanation framework supporting iterative model restriction. We demonstrate its benefits in a second user study.
APA, Harvard, Vancouver, ISO, and other styles
9

Fogelin, Lars. "Inference to the Best Explanation: A Common and Effective Form of Archaeological Reasoning." American Antiquity 72, no. 4 (October 2007): 603–26. http://dx.doi.org/10.2307/25470436.

Full text
Abstract:
Processual and postprocessual archaeologists implicitly employ the same epistemological system to evaluate the worth of different explanations: inference to the best explanation. This is good since inference to the best explanation is the most effective epistemological approach to archaeological reasoning available. Underlying the logic of inference to the best explanation is the assumption that the explanation that accounts for the most evidence is also most likely to be true. This view of explanation often reflects the practice of archaeological reasoning better than either the hypothetico-deductive method or hermeneutics. This article explores the logic of inference to the best explanation and provides clear criteria to determine what makes one explanation better than another. Explanations that are empirically broad, general, modest, conservative, simple, testable, and address many perspectives are better than explanations that are not. This article also introduces a system of understanding explanation that emphasizes the role of contrastive pairings in the construction of specific explanations. This view of explanation allows for a better understanding of when, and when not, to engage in the testing of specific explanations.
APA, Harvard, Vancouver, ISO, and other styles
10

Veugen, Thijs, Bart Kamphorst, and Michiel Marcus. "Privacy-Preserving Contrastive Explanations with Local Foil Trees." Cryptography 6, no. 4 (October 28, 2022): 54. http://dx.doi.org/10.3390/cryptography6040054.

Full text
Abstract:
We present the first algorithm that combines privacy-preserving technologies and state-of-the-art explainable AI to enable privacy-friendly explanations of black-box AI models. We provide a secure algorithm for contrastive explanations of black-box machine learning models that securely trains and uses local foil trees. Our work shows that the quality of these explanations can be upheld whilst ensuring the privacy of both the training data and the model itself.
APA, Harvard, Vancouver, ISO, and other styles
More sources

Dissertations / Theses on the topic "Contrastive Explanations"

1

Olbrich, David. "Normativity and contrastive explanation." Thesis, University College London (University of London), 2016. http://discovery.ucl.ac.uk/1474151/.

Full text
Abstract:
My thesis concentrates on the distinction between pro tanto reasons and all-things-considered judgments, and their relation to normative justification. Negatively, it seeks to show that a prevailing kind of account of this relation should be rejected, namely that family of views which takes it that every reason has an associated weight, and the truth with respect to any issue is established by which set of reasons is weightiest. Through an examination of Ross’ doctrine of prima facie duties, this discussion also leads to a formulation of the central problem which any account of this relation must seek to solve. Positively, this thesis develops a new account of the relation between pro tanto reasons and all-things-considered judgements, based on the fundamental insight that a justification of normative propositions is identical to an explanation of their truth, were they to be true. I defend this identity claim, and seek to generate an account of justification from an account of explanation. Drawing on a deservedly popular ‘contrastive’ conception of explanation in the philosophy of science, I show how we can fruitfully think of justification as itself contrastive. Part of this is showing how the notion of a burden of explanation can shed light on the notion of a burden of justification, so a conception of justification emerges according to which a justification for a normative proposition consists in an solution to all those burdens of justification which it incurs. In turn, this feeds a conception of reasons, and their role in justification, alternative to that envisaged in a weighing model: pro tanto reasons determine the correct all-things-considered judgment insofar as they determine to what extent the truth of that judgement has an adequate explanation, such that the correct all-things-considered judgement is just that judgement whose truth would have a fully adequate explanation.
APA, Harvard, Vancouver, ISO, and other styles
2

Le, Poire Beth Ann. "Two contrasting explanations of involvement violations: Orientation response or affective reaction?" Diss., The University of Arizona, 1991. http://hdl.handle.net/10150/185729.

Full text
Abstract:
Among theories that address the impact of variations in immediacy behaviors during ongoing interactions are nonverbal expectancy violations and discrepancy arousal theories. This study of the effects of violations of expectations on arousal and reciprocity and compensation in the medical student-patient relationship proposed that (1) nonverbal expectancy violations theory would be more valid than discrepancy arousal theory in predicting outcomes, (2) violations of expectations would be followed by an orientation response as indicated by both physiological indicators and nonverbal behaviors, and (3) physiological indicators of arousal intensity would be associated with nonverbal indicators of arousal intensity. The results indicate that neither nonverbal expectancy violations nor discrepancy arousal theory's predictions were entirely valid, as high and very high involvement (including touch and close proximity) were met with reciprocity of high involvement, while low and very low involvement (negative violations of expectations) were met with reciprocity of low involvement. Additionally, all violations of expectations were followed by increases in arousal rather than the orientation response. Finally, arousal was generally predictive of nonverbal indicators of arousal intensity, thus offering less obtrusive ways to measure arousal.
APA, Harvard, Vancouver, ISO, and other styles
3

Genuchten, Erlijn Wendela van [Verfasser], and Katharina [Akademischer Betreuer] Scheiter. "Why Pictures are Beneficial to Learning : Contrasting Explanations of the Multimedia Effect / Erlijn Wendela van Genuchten ; Betreuer: Katharina Scheiter." Tübingen : Universitätsbibliothek Tübingen, 2013. http://d-nb.info/1162896973/34.

Full text
APA, Harvard, Vancouver, ISO, and other styles

Books on the topic "Contrastive Explanations"

1

Kendall, Jeremy. The third sector and social care for older people in England: Towards an explanation of its contrasting contributions in residential care, domiciliary care and day care.. London: London School of Economics. Centre for Civil Society, 2000.

Find full text
APA, Harvard, Vancouver, ISO, and other styles
2

Martins-Frias, Adriana, and Susana Gil Llinás. Cruzando la raya 2, Coursebook of spanish for lusofalantes (A2-B1). Imprensa Universidade de Évora, 2022. http://dx.doi.org/10.24902/uevora.28.

Full text
Abstract:
The proximity between Spanish and Portuguese is both an advantage and a drawback for Portuguese-speaking students who are beginning to study Spanish. The similarities between both languages allow learners to advance easily through the initial levels of Spanish, but, at the same time, cause recurrent interference mistakes that are commonly shared. Taking these peculiarities into account, the Cruzando la Raya 2 coursebook was created for university students of Spanish whose mother tongue is Portuguese. This coursebook follows a communicative and contrastive approach by offering explanations, semantic notes or exercises that emphasize the similarities and differences between Spanish and Portuguese in order to promote a more effective learning of the Spanish language.
APA, Harvard, Vancouver, ISO, and other styles
3

Menzies, Peter. Platitudes and Counterexamples. Edited by Helen Beebee, Christopher Hitchcock, and Peter Menzies. Oxford University Press, 2010. http://dx.doi.org/10.1093/oxfordhb/9780199279739.003.0018.

Full text
Abstract:
This article explains the conception of causation as a natural relation in more detail. It outlines some of the features of our use of the causal concept that do not fit with the idea of causation as a natural relation between events. It then outlines the correct explanation of these features, replacing the metaphysical conception of causation with a conception of causation in terms of a contrastive difference-making relation, where the contrasts are determined contextually on the basis of what are often normative considerations.
APA, Harvard, Vancouver, ISO, and other styles
4

Cherchali, Katie. How can contrastive analysis, error analysis and interlanguage studies help in the identification, categorisation and explanation of commonly occurring errors in Japanese learners' written academic English. 1995.

Find full text
APA, Harvard, Vancouver, ISO, and other styles
5

Chakravartty, Anjan. Knowledge Under Ontological Uncertainty. Oxford University Press, 2017. http://dx.doi.org/10.1093/oso/9780190651459.003.0006.

Full text
Abstract:
The first of two forms of ontological uncertainty arising in previous chapters is examined in detail. This first form stems from situations in which our best scientific theorizing or modeling with respect to one and the same target system or phenomenon in the world generates what appear to be mutually inconsistent descriptions. A recent, popular response to the challenge this represents—for anyone hoping for a coherent conception of scientific ontology—is to invoke a form of “perspectivism” regarding these descriptions. However, while certain forms of pluralism may be apt in such cases, perspectivism is not one of them. It is argued that perspectival accounts of ontology are subject to a fatal trilemma. Two forms of non-perspectival pluralism are described, supporting the introduction of a novel, contrastive theory of ontological explanation.
APA, Harvard, Vancouver, ISO, and other styles
6

Parsons, Laurel, and Brenda Ravenscroft. Josephine Lang, “An einer Quelle” (1840/1853) and “Am Morgen” (1840). Oxford University Press, 2018. http://dx.doi.org/10.1093/oso/9780190237028.003.0008.

Full text
Abstract:
Among the approximately 300 songs of Josephine Lang (1815–1880), there are several instances of setting the same text to strikingly different music. This chapter discusses Lang’s contrasting settings of two poems by Reinhold Köstlin. Her three settings of “Wenn das Herz dir ist beklommen” (two composed in 1840, the third in 1853) exhibit similarities in vocal rhythm and in motivic structure, but differ in key, in accompaniment pattern, and, most obviously, in mood. The two settings of “Am Morgen” (composed three days apart in 1840) are in the same key and share certain patterns of line repetition, but diverge in tempo, accompaniment pattern, and mood. Documentary evidence provides some possible explanations for Lang’s changes in her approach to the poems.
APA, Harvard, Vancouver, ISO, and other styles
7

Pencavel, John H. A Brief History of Working Hours. Oxford University Press, 2018. http://dx.doi.org/10.1093/oso/9780190876166.003.0002.

Full text
Abstract:
Why did the length of the work day and work week decline in the nineteenth and early twentieth centuries? In this chapter, the author explores possible explanations for these declines, contrasting events and trends in Britain and America, including the activities of trade unions, employers, statutory legislation, and the workings of labor markets. Classical economists tended to support the position taken by many employers which was to resist both legislation on hours and the efforts of trade unions to reduce hours. In the few instances in which the Classical economists provided precise reasons for their view, they made assumptions about the manner in which hours enter a firm’s production function. These assumptions can be tested which is the subject of the subsequent chapter.
APA, Harvard, Vancouver, ISO, and other styles
8

Miller, Kenneth P. Texas vs. California. Oxford University Press, 2020. http://dx.doi.org/10.1093/oso/9780190077365.001.0001.

Full text
Abstract:
Texas and California are the leaders of red and blue America. As the nation has polarized, its most populous and economically powerful states have taken charge of the opposing camps. These states now advance sharply contrasting political and policy agendas and view themselves as competitors for control of the nation’s future. This book provides a detailed account of the rivalry’s emergence, present state, and possible future. First, it explores why, despite their many similarities, the two states have become so deeply divided. The explanations focus on critical differences in the state’s origins as well as in their later demographic, economic, cultural, and political development. Second, the book analyzes how the two states have translated their competing visions into policy. It describes how Texas and California have constructed opposing, comprehensive policy models—one conservative, the other progressive. It describes how these models operate and how they have produced widely different outputs in a range of domestic policy areas. In separate chapters, the book highlights the states’ contrasting policies in five areas: tax, labor, energy and environment, poverty, and social issues. It also shows how Texas and California have led the red and blue state blocs in seeking to influence federal policy in these and other areas. Finally, the book assesses the two models’ strengths, vulnerabilities, and potential futures, providing a balanced analysis of their competing visions.
APA, Harvard, Vancouver, ISO, and other styles
9

Assael, Brenda. Running the Restaurant. Oxford University Press, 2018. http://dx.doi.org/10.1093/oso/9780198817604.003.0003.

Full text
Abstract:
Chapter 2 examines the restaurant as a business. It offers an explanation for the dramatically contrasting fortunes of London’s restaurants, a sector of the economy characterized by success and expansion as well as by failure and bankruptcy. Consideration is given to how restaurants were financed, how they secured staff and supplies, the incorporation of new technology, and the often ingenious ways that they sought out customers. Restaurant proprietors and managers (and even cooks and chefs) explored a variety of schemes to establish their status as professionals, but these rarely compromised the vigorous pursuit of financial reward, in a sector of the economy in which profit margins were often relatively small. In an era characterized by a moving frontier between state and economy, the restaurant revealed the ongoing commitment in Victorian and Edwardian culture to the power of free enterprise and the maintenance of a robust commercial domain.
APA, Harvard, Vancouver, ISO, and other styles
10

Hanhimäki, Jussi M. Europe's Cold War. Edited by Dan Stone. Oxford University Press, 2012. http://dx.doi.org/10.1093/oxfordhb/9780199560981.013.0014.

Full text
Abstract:
In 1945, much of Europe was in rubble, following an orgy of violence and genocide unprecedented in recorded history. This alone provides one explanation for the phenomenal rise of Soviet and American power in Europe after World War II. And given the ideological differences, material capabilities, security interests, and contrasting personalities of those in power, it was no wonder that any possibility of cooperation between the Soviet Union and the United States vanished after the common objective of defeating the Axis powers had been achieved. While the Cold War may not have been inevitable, it would have been difficult to avoid. This article explores the evolution of transatlantic relations during the Cold War, with particular emphasis on Geir Lundestad's thesis about ‘empire by invitation’. It then turns to the other side of the Cold War divide and evaluates the supposed omnipotence of the Soviet Union over its client states. The article also examines the cracks in the Iron Curtain – the evolution of relations between, beneath, and beyond the two blocs in Europe.
APA, Harvard, Vancouver, ISO, and other styles

Book chapters on the topic "Contrastive Explanations"

1

Boulter, Stephen. "Contrastive Explanations in Evolutionary Biology." In Classifying Reality, 61–77. Chichester, UK: John Wiley & Sons, Ltd, 2013. http://dx.doi.org/10.1002/9781118627747.ch4.

Full text
APA, Harvard, Vancouver, ISO, and other styles
2

Mishra, Pradeepta. "Contrastive Explanations for Machine Learning." In Practical Explainable AI Using Python, 279–98. Berkeley, CA: Apress, 2021. http://dx.doi.org/10.1007/978-1-4842-7158-2_11.

Full text
APA, Harvard, Vancouver, ISO, and other styles
3

Kean, Alex. "A characterization of contrastive explanations computation." In PRICAI’98: Topics in Artificial Intelligence, 599–610. Berlin, Heidelberg: Springer Berlin Heidelberg, 1998. http://dx.doi.org/10.1007/bfb0095304.

Full text
APA, Harvard, Vancouver, ISO, and other styles
4

Artelt, André, Fabian Hinder, Valerie Vaquet, Robert Feldhans, and Barbara Hammer. "Contrastive Explanations for Explaining Model Adaptations." In Advances in Computational Intelligence, 101–12. Cham: Springer International Publishing, 2021. http://dx.doi.org/10.1007/978-3-030-85030-2_9.

Full text
APA, Harvard, Vancouver, ISO, and other styles
5

Koopman, Tara, and Silja Renooij. "Persuasive Contrastive Explanations for Bayesian Networks." In Lecture Notes in Computer Science, 229–42. Cham: Springer International Publishing, 2021. http://dx.doi.org/10.1007/978-3-030-86772-0_17.

Full text
APA, Harvard, Vancouver, ISO, and other styles
6

Apicella, A., F. Isgrò, R. Prevete, and G. Tamburrini. "Contrastive Explanations to Classification Systems Using Sparse Dictionaries." In Lecture Notes in Computer Science, 207–18. Cham: Springer International Publishing, 2019. http://dx.doi.org/10.1007/978-3-030-30642-7_19.

Full text
APA, Harvard, Vancouver, ISO, and other styles
7

Veugen, Thijs, Bart Kamphorst, and Michiel Marcus. "Privacy-Preserving Contrastive Explanations with Local Foil Trees." In Cyber Security, Cryptology, and Machine Learning, 88–98. Cham: Springer International Publishing, 2022. http://dx.doi.org/10.1007/978-3-031-07689-3_7.

Full text
APA, Harvard, Vancouver, ISO, and other styles
8

Koopman, Tara, and Silja Renooij. "Correction to: Persuasive Contrastive Explanations for Bayesian Networks." In Lecture Notes in Computer Science, C1. Cham: Springer International Publishing, 2021. http://dx.doi.org/10.1007/978-3-030-86772-0_49.

Full text
APA, Harvard, Vancouver, ISO, and other styles
9

Ignatiev, Alexey, Nina Narodytska, Nicholas Asher, and Joao Marques-Silva. "From Contrastive to Abductive Explanations and Back Again." In AIxIA 2020 – Advances in Artificial Intelligence, 335–55. Cham: Springer International Publishing, 2021. http://dx.doi.org/10.1007/978-3-030-77091-4_21.

Full text
APA, Harvard, Vancouver, ISO, and other styles
10

Labaien, Jokin, Ekhi Zugasti, and Xabier De Carlos. "Contrastive Explanations for a Deep Learning Model on Time-Series Data." In Big Data Analytics and Knowledge Discovery, 235–44. Cham: Springer International Publishing, 2020. http://dx.doi.org/10.1007/978-3-030-59065-9_19.

Full text
APA, Harvard, Vancouver, ISO, and other styles

Conference papers on the topic "Contrastive Explanations"

1

Artelt, Andre, and Barbara Hammer. "Efficient computation of contrastive explanations." In 2021 International Joint Conference on Neural Networks (IJCNN). IEEE, 2021. http://dx.doi.org/10.1109/ijcnn52387.2021.9534454.

Full text
APA, Harvard, Vancouver, ISO, and other styles
2

Pillai, Vipin, Soroush Abbasi Koohpayegani, Ashley Ouligian, Dennis Fong, and Hamed Pirsiavash. "Consistent Explanations by Contrastive Learning." In 2022 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR). IEEE, 2022. http://dx.doi.org/10.1109/cvpr52688.2022.00997.

Full text
APA, Harvard, Vancouver, ISO, and other styles
3

Prabhushankar, Mohit, Gukyeong Kwon, Dogancan Temel, and Ghassan AlRegib. "Contrastive Explanations In Neural Networks." In 2020 IEEE International Conference on Image Processing (ICIP). IEEE, 2020. http://dx.doi.org/10.1109/icip40778.2020.9190927.

Full text
APA, Harvard, Vancouver, ISO, and other styles
4

Jacovi, Alon, Swabha Swayamdipta, Shauli Ravfogel, Yanai Elazar, Yejin Choi, and Yoav Goldberg. "Contrastive Explanations for Model Interpretability." In Proceedings of the 2021 Conference on Empirical Methods in Natural Language Processing. Stroudsburg, PA, USA: Association for Computational Linguistics, 2021. http://dx.doi.org/10.18653/v1/2021.emnlp-main.120.

Full text
APA, Harvard, Vancouver, ISO, and other styles
5

Sreedharan, Sarath, Siddharth Srivastava, and Subbarao Kambhampati. "Hierarchical Expertise Level Modeling for User Specific Contrastive Explanations." In Twenty-Seventh International Joint Conference on Artificial Intelligence {IJCAI-18}. California: International Joint Conferences on Artificial Intelligence Organization, 2018. http://dx.doi.org/10.24963/ijcai.2018/671.

Full text
Abstract:
There is a growing interest within the AI research community in developing autonomous systems capable of explaining their behavior to users. However, the problem of computing explanations for users of different levels of expertise has received little research attention. We propose an approach for addressing this problem by representing the user's understanding of the task as an abstraction of the domain model that the planner uses. We present algorithms for generating minimal explanations in cases where this abstract human model is not known. We reduce the problem of generating an explanation to a search over the space of abstract models and show that while the complete problem is NP-hard, a greedy algorithm can provide good approximations of the optimal solution. We also empirically show that our approach can efficiently compute explanations for a variety of problems.
APA, Harvard, Vancouver, ISO, and other styles
6

Paranjape, Bhargavi, Julian Michael, Marjan Ghazvininejad, Hannaneh Hajishirzi, and Luke Zettlemoyer. "Prompting Contrastive Explanations for Commonsense Reasoning Tasks." In Findings of the Association for Computational Linguistics: ACL-IJCNLP 2021. Stroudsburg, PA, USA: Association for Computational Linguistics, 2021. http://dx.doi.org/10.18653/v1/2021.findings-acl.366.

Full text
APA, Harvard, Vancouver, ISO, and other styles
7

Chen, Shenghui, Kayla Boggess, and Lu Feng. "Towards Transparent Robotic Planning via Contrastive Explanations." In 2020 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS). IEEE, 2020. http://dx.doi.org/10.1109/iros45743.2020.9341773.

Full text
APA, Harvard, Vancouver, ISO, and other styles
8

Bloch, Isabelle, and Marie-Jeanne Lesot. "Towards a Formulation of Fuzzy Contrastive Explanations." In 2022 IEEE International Conference on Fuzzy Systems (FUZZ-IEEE). IEEE, 2022. http://dx.doi.org/10.1109/fuzz-ieee55066.2022.9882887.

Full text
APA, Harvard, Vancouver, ISO, and other styles
9

Huang, Xuanxiang, Yacine Izza, Alexey Ignatiev, and Joao Marques-Silva. "On Efficiently Explaining Graph-Based Classifiers." In 18th International Conference on Principles of Knowledge Representation and Reasoning {KR-2021}. California: International Joint Conferences on Artificial Intelligence Organization, 2021. http://dx.doi.org/10.24963/kr.2021/34.

Full text
Abstract:
Recent work has shown that not only decision trees (DTs) may not be interpretable but also proposed a polynomial-time algorithm for computing one PI-explanation of a DT. This paper shows that for a wide range of classifiers, globally referred to as decision graphs, and which include decision trees and binary decision diagrams, but also their multi-valued variants, there exist polynomial-time algorithms for computing one PI-explanation. In addition, the paper also proposes a polynomial-time algorithm for computing one contrastive explanation. These novel algorithms build on explanation graphs (XpG's). XpG's denote a graph representation that enables both theoretical and practically efficient computation of explanations for decision graphs. Furthermore, the paper proposes a practically efficient solution for the enumeration of explanations, and studies the complexity of deciding whether a given feature is included in some explanation. For the concrete case of decision trees, the paper shows that the set of all contrastive explanations can be enumerated in polynomial time. Finally, the experimental results validate the practical applicability of the algorithms proposed in the paper on a wide range of publicly available benchmarks.
APA, Harvard, Vancouver, ISO, and other styles
10

Sokol, Kacper, and Peter Flach. "Conversational Explanations of Machine Learning Predictions Through Class-contrastive Counterfactual Statements." In Twenty-Seventh International Joint Conference on Artificial Intelligence {IJCAI-18}. California: International Joint Conferences on Artificial Intelligence Organization, 2018. http://dx.doi.org/10.24963/ijcai.2018/836.

Full text
Abstract:
Machine learning models have become pervasive in our everyday life; they decide on important matters influencing our education, employment and judicial system. Many of these predictive systems are commercial products protected by trade secrets, hence their decision-making is opaque. Therefore, in our research we address interpretability and explainability of predictions made by machine learning models. Our work draws heavily on human explanation research in social sciences: contrastive and exemplar explanations provided through a dialogue. This user-centric design, focusing on a lay audience rather than domain experts, applied to machine learning allows explainees to drive the explanation to suit their needs instead of being served a precooked template.
APA, Harvard, Vancouver, ISO, and other styles
You might also be interested in the extended bibliographies on the topic 'Contrastive Explanations' for particular source types:
Journal articles
We offer discounts on all premium plans for authors whose works are included in thematic literature selections. Contact us to get a unique promo code!

To the bibliography