Filters








8,653 Hits in 9.1 sec

Efficient compositional modeling for generating causal explanations

P.Pandurang Nayak, Leo Joskowicz
1996 Artificial Intelligence  
Second, we show how the structural, behavioral, and functional contexts of the device define model adequacy and provide the task focus and additional constraints to guide the search for adequate models  ...  This paper addresses the reasoning and knowledge representation issues that arise in building practical systems for constructing adequate device models that provide parsimonious causal explanations of  ...  Sanjaya Addanki collaborated in the initial phase of this project. We also thank the anonymous reviewers of Artificial Intelligence for suggesting many improvements to the original manuscript.  ... 
doi:10.1016/0004-3702(95)00024-0 fatcat:4llxi4xsubgfdko5eqsrzn5ovm

State of the Art in Fair ML: From Moral Philosophy and Legislation to Fair Classifiers [article]

Elias Baumann, Josef Lorenz Rumberger
2018 arXiv   pre-print
This work aims to give an introduction into discrimination, legislative foundations to counter it and strategies to detect and prevent machine learning algorithms from showing such behavior.  ...  With the recent General Data Protection Regulation (GDPR) coming into effect, new awareness has been raised for such issues and with computer scientists having such a large impact on peoples lives it is  ...  [49] provide an algorithm that no longer requires an exact causal model but instead allows for an approximation of counterfactual fairness across multiple causal models.  ... 
arXiv:1811.09539v1 fatcat:7e7hkumg2faffhmrgjvdxo2oiu

Flexible Heuristics Miner (FHM)

A.J.M.M. Weijters, J.T.S. Ribeiro
2011 2011 IEEE Symposium on Computational Intelligence and Data Mining (CIDM)  
The new process representation language and mining technique can also be used for conformance checking; to indicate if all the behavior in the event log is also represented in the process model and if  ...  To overcome these problems, a new process representation language (i.e. augmented Causal nets) is presented in combination with an accompanying process mining algorithm.  ...  Using the event log introduced in Section 1, it is intended to show how the FHM can provide insight about very flexible applications.  ... 
doi:10.1109/cidm.2011.5949453 dblp:conf/cidm/WeijtersR11 fatcat:7kxefabkorc7vdtkxw3t4cxk2i

Counterfactuals and Causability in Explainable Artificial Intelligence: Theory, Algorithms, and Applications [article]

Yu-Liang Chou and Catarina Moreira and Peter Bruza and Chun Ouyang and Joaquim Jorge
2021 arXiv   pre-print
This paper presents an in-depth systematic review of the diverse existing body of literature on counterfactuals and causability for explainable artificial intelligence.  ...  This research suggests that current model-agnostic counterfactual algorithms for explainable AI are not grounded on a causal theoretical formalism and, consequently, cannot promote causability to a human  ...  The What-If tool [112] provides an excellent example, enabling people to visualize model behavior across multiple models and subsets of input data and for different ML fairness metrics.  ... 
arXiv:2103.04244v2 fatcat:uqs3y7v7hrhtxkh2ltl4wluyqe

The Design and Implementation of an Active Peer Agent Providing Personalized User Interface [chapter]

Kwangsu Cho, Sung-il Kim, Sung-Hyun Yun
2005 Lecture Notes in Computer Science  
This study describes the design and implementation of a naive computer peer agent called KORI-2.  ...  In addition, the KORI-2 system implements interface to contextualize the navigational situations of human tutors. Corresponding Author.  ...  Acknowledgments This research was supported by Brain informatics Research Program sponsored by Korea Ministry of Science and Technology.  ... 
doi:10.1007/11552413_10 fatcat:dxswlaulefff3dn5uiqiufv4ne

Machine Reasoning Explainability [article]

Kristijonas Cyras, Ramamurthy Badrinath, Swarup Kumar Mohalik, Anusha Mujumdar, Alexandros Nikou, Alessandro Previti, Vaishnavi Sundararajan, Aneta Vulgarakis Feljan
2020 arXiv   pre-print
We hereby aim to provide a selective overview of MR explainability techniques and studies in hopes that insights from this long track of research will complement well the current XAI landscape.  ...  As a field of AI, Machine Reasoning (MR) uses largely symbolic means to formalize and emulate abstract reasoning.  ...  an algorithm for computing corrective explanations of minimal length.  ... 
arXiv:2009.00418v2 fatcat:wvx77eo73jeb7eplcpz42lw3zq

When one model casts doubt on another: A levels-of-analysis approach to causal discounting

Sangeet S. Khemlani, Daniel M. Oppenheimer
2011 Psychological bulletin  
Theories of causal discounting at the computational level attempt to provide normative, prescriptive explanations for discounting behavior, and they build on other normative frameworks like formal logic  ...  We provide a survey of the descriptive and formal models that attempt to explain the discounting process and summarize what current models do not account for and where room for improvement exists.  ...  Theories at the computational level attempt to provide normative, prescriptive explanations for discounting behavior, and they build on other normative frameworks like formal logic and probability theory  ... 
doi:10.1037/a0021809 pmid:21142348 fatcat:z62tzx4tfzc4tm5isxozri6be4

Interpretable Data-Based Explanations for Fairness Debugging [article]

Romila Pradhan, Jiongli Zhu, Boris Glavic, Babak Salimi
2021 arXiv   pre-print
In this work, we introduce Gopher, a system that produces compact, interpretable, and causal explanations for bias or unexpected model behavior by identifying coherent subsets of the training data that  ...  Our experimental evaluation demonstrates the effectiveness of Gopher in generating interpretable explanations for identifying and debugging sources of bias.  ...  data-based explanations that relate an unexpected and discriminatory behavior of an ML algorithm to its training data, not its input features.  ... 
arXiv:2112.09745v1 fatcat:2tfjxr7kg5f33eiovymhbbm3sq

Concepts and tools of artificial intelligence for human decision making

Anna Vari, Janos Vecsenyi
1988 Acta Psychologica  
Even as novel algorithms for explanation are being developed, researchers have called for more human interpretability.  ...  The increasing ubiquity of artificial intelligence (AI) has spurred the development of explainable AI (XAI) to make AI more understandable.  ...  For example, to find the cause of an application behavior, user could seek a contrastive explanation of counterfactuals to filter causes (grey arrow); this can be supported with why not and how to explanations  ... 
doi:10.1016/0001-6918(88)90057-1 fatcat:7dp34vc7p5g4togbq2x47uydbe

How Circuits Work [chapter]

Johan De Kleer
1984 Qualitative Reasoning About Physical Systems  
One aspect of the theory. causal analysis. describes how the behavior of the individual components can be combined to explain the behavior of composite systems.  ...  This intuitive reasoning provides a great deal of important information about the operation of the circuit, which although qualitative in nature, describes important quantitative aspects of circuit functioning  ...  Jeff Shrager. and Brian \Villiams pro\ ided many useful comments on the paper.  ... 
doi:10.1016/b978-0-444-87670-6.50008-x fatcat:7hhq5m44qbfc3cs5m23vcmixlq

How circuits work

Johan De Kleer
1984 Artificial Intelligence  
One aspect of the theory. causal analysis. describes how the behavior of the individual components can be combined to explain the behavior of composite systems.  ...  This intuitive reasoning provides a great deal of important information about the operation of the circuit, which although qualitative in nature, describes important quantitative aspects of circuit functioning  ...  Jeff Shrager. and Brian \Villiams pro\ ided many useful comments on the paper.  ... 
doi:10.1016/0004-3702(84)90040-7 fatcat:wdjw6in7tjckjme3ftptny4fmq

A Multivariate Granger Causality Concept towards Full Brain Functional Connectivity

Christoph Schmidt, Britta Pester, Nicole Schmid-Hertel, Herbert Witte, Axel Wismüller, Lutz Leistritz, Adam J Schwarz
2016 PLoS ONE  
Our large scale Granger Causality approach is applied to synthetic and resting state fMRI data with a focus on how well network community structure, which represents a functional segmentation of the network  ...  This concept is comprised of an orthogonal back projection of LD MVAR model residuals to HD space and using these back-transferred residuals for proper definitions of vertex by vertex interactions.  ...  Lutz Leistritz and Axel Wismueller jointly contributed to the initial idea of the large-scale Granger Causality Index. Author Contributions  ... 
doi:10.1371/journal.pone.0153105 pmid:27064897 pmcid:PMC4827851 fatcat:nou4kmy7hrfddizbvr2q6235pe

Knowledge-based support for a physician's workstation

W M Stanton, P C Tang
1991 Proceedings. Symposium on Computer Applications in Medical Care  
We present the motivation behind our design, discuss the components of the knowledge base, and show how the knowledge base supports a physician's workstation in the patient management process.  ...  We describe a graphical knowledge base editor used by the domain expert for knowledge acquisition, and a graphical knowledge base presenter which monitors the qualitative simulation during patient event  ...  Using a causal model, when such knowledge exists, allows the system to represent behavior due to a number of stimuli through a common physiological pathway; it is concise and flexible.  ... 
pmid:1807683 pmcid:PMC2247611 fatcat:e3nip3f3iffzpirm2gvvckf54u

Appendix A A Guide for Newcomers to Agent-Based Modeling in the Social Sciences [chapter]

Robert Axelrod, Leigh Tesfatsion
2006 Handbook of Computational Economics  
For the original work, including agent-based models, formal theorems, and many real-world applications, see Robert Axelrod, Evolution of Cooperation (1984, NY: Basic Books) .  ...  ABM researchers seek causal explanations grounded in the repeated interactions of agents operating in specified environments.  ... 
doi:10.1016/s1574-0021(05)02044-7 fatcat:3h7f2m6a5rbkhpkxpedck2zjke

Discovering models of software processes from event-based data

Jonathan E. Cook, Alexander L. Wolf
1998 ACM Transactions on Software Engineering and Methodology  
The three methods range from the purely algorithmic to the purely statistical. We compare the methods and discuss their application in an industrial case study.  ...  Under this technique, data describing process events are first captured from an on-going process and then used to generate a formal model of the behavior of that process.  ...  ACKNOWLEDGMENTS We appreciate the many helpful comments on this work provided by Clarence (Skip) Ellis, Dennis Heimbigner, David Rosenblum, Lawrence Votta, and Benjamin Zorn, as well as the anonymous reviewers  ... 
doi:10.1145/287000.287001 fatcat:32ko52e3andovldotayee44nbi
« Previous Showing results 1 — 15 out of 8,653 results