Filters








623,075 Hits in 3.4 sec

Requirements for Explainable Smart Systems in the Enterprises from Users and Society Based on FAT

Yuri Nakao, Junichi Shigezumi, Hikaru Yokono, Takuya Takagi
2019 International Conference on Intelligent User Interfaces  
As statistical methods for smart systems prevail, requirements related to explainability based on fairness, accountability, and transparency (FAT) become stronger.  ...  While end users need to confirm the fairness of the output of smart systems at a glance, society needs thorough explanations based on FAT.  ...  For example, in the field of machine learning, there are two definitions of fairness: group fairness and individual fairness [17, 32] .  ... 
dblp:conf/iui/NakaoSYT19 fatcat:2xvvrrtymje5xnvad2zfzndvuy

Algorithmic Impact Assessment: Fairness, Robustness and Explainability in Automated Decision-Making

Adriano Koshiyama, Zeynep Engin
2019 Zenodo  
The workshop session focuses on the following topics: Introduction to AI & Machine Learning (Algorithms) Key Components of Algorithmic Impact Assessment Algorithmic Explainability Algorithmic Fairness  ...  ❖Did Mathematical definition of Fairness ❖ There are multiple sources of bias that explain how an automated decision-making process becomes unfair ❖ Tainted examples: Any ML system keeps the bias existing  ...  into groups defined by protected attributes and seeks for some measure to be equal groups Mathematical definition of Fairness ❖ Also, within Group fairness, it is possible to distinguish between the  ... 
doi:10.5281/zenodo.3361708 fatcat:bcpolfbaaff4zn5hbhjvudypca

Algorithm Impact Assessment: Fairness, Robustness and Explainability in Automated Decision-Making

Adriano Koshiyama, Zeynep Engin
2019 Zenodo  
The workshop session focuses on the following topics: Introduction to AI & Machine Learning (Algorithms) Key Components of Algorithm Impact Assessment Algorithm Explainability Algorithm Fairness Algorithm  ...  Mathematical definition of Fairness Mathematical definition of Fairness ❖ Also, within Group fairness, it is possible to distinguish between the aim of Equality of Opportunity and Outcome.  ...  ❖Did you ensure an adequate working definition of "fairness" that you apply in designing AI systems?  ... 
doi:10.5281/zenodo.3241853 fatcat:y5hczryzqjeblovl7ss2pqeme4

Algorithm Impact Assessment: Fairness, Robustness and Explainability in Automated Decision-Making

Adriano Koshiyama, Zeynep Engin
2019 Zenodo  
The workshop session focuses on the following topics: Introduction to AI & Machine Learning (Algorithms) Key Components of Algorithm Impact Assessment Algorithm Explainability Algorithm Fairness Algorithm  ...  Mathematical definition of Fairness Mathematical definition of Fairness ❖ Also, within Group fairness, it is possible to distinguish between the aim of Equality of Opportunity and Outcome.  ...  ❖Did you ensure an adequate working definition of "fairness" that you apply in designing AI systems?  ... 
doi:10.5281/zenodo.3241980 fatcat:nyrlybmuyfd5zlluwhmr65bjby

Technologies for Trustworthy Machine Learning: A Survey in a Socio-Technical Context [article]

Ehsan Toreini, Mhairi Aitken, Kovila P. L. Coopamootoo, Karen Elliott, Vladimiro Gonzalez Zelaya, Paolo Missier, Magdalene Ng, Aad van Moorsel
2022 arXiv   pre-print
We argue that four categories of system properties are instrumental in achieving the policy objectives, namely fairness, explainability, auditability and safety & security (FEAS).  ...  Concerns about the societal impact of AI-based services and systems has encouraged governments and other organisations around the world to propose AI policy frameworks to address fairness, accountability  ...  Definitions and Implementation of Fairness.  ... 
arXiv:2007.08911v3 fatcat:gmswdvel6bdbvg5rvyzb2uygbu

Engaging undergraduates in copyright and fair use fundamentals

Kyra Folk-Farber
2016 College & Undergraduate Libraries  
the ethics around copyright law, of their rights over their own contributions to their scholarly communities, of the availability of Creative Commons-licensed materials, and of how to exercise their fair  ...  With this in mind, I designed an undergraduate class on copyright and fair use fundamentals that can be incorporated into any introductory college or university library instruction course or can be treated  ...  Each group must choose a representative to explain whether or not the video falls under fair use, and to defend the group's decision using evidence.  ... 
doi:10.1080/10691316.2016.1245020 fatcat:elheaxu25remzocss7td5kpdbq

Towards the Right Kind of Fairness in AI [article]

Boris Ruf, Marcin Detyniecki
2021 arXiv   pre-print
Fairness is a concept of justice. Various definitions exist, some of them conflicting with each other.  ...  Therefore, we first structure the complex landscape of existing fairness metrics and explain the different options by example.  ...  Second, we explain the problem of unwanted bias in data. Next, we present the most commonly used fairness definitions in research and explain the ethical principles they stand for.  ... 
arXiv:2102.08453v7 fatcat:tnpjk2oponfzhkchwptxc2flye

Fast and Efficient MMD-Based Fair PCA via Optimization over Stiefel Manifold

Junghyun Lee, Gwangsu Kim, Mahbod Olfat, Mark Hasegawa-Johnson, Chang D. Yoo
2022 PROCEEDINGS OF THE THIRTIETH AAAI CONFERENCE ON ARTIFICIAL INTELLIGENCE AND THE TWENTY-EIGHTH INNOVATIVE APPLICATIONS OF ARTIFICIAL INTELLIGENCE CONFERENCE  
Experimental comparisons based on synthetic and UCI datasets show that our approach outperforms prior work in explained variance, fairness, and runtime.  ...  The incorporation of MMD naturally leads to an exact and tractable mathematical formulation of fairness with good statistical properties.  ...  Figure 2 plots the explained variance and fairness metric values. Observe how MBF-PCA achieves better explained variance, while achieving similar level of fairness.  ... 
doi:10.1609/aaai.v36i7.20699 fatcat:xbwylqpjmrc75pcmsnoqkjvjsm

Fast and Efficient MMD-based Fair PCA via Optimization over Stiefel Manifold [article]

Junghyun Lee, Gwangsu Kim, Matt Olfat, Mark Hasegawa-Johnson, Chang D. Yoo
2022 arXiv   pre-print
Experimental comparisons based on synthetic and UCI datasets show that our approach outperforms prior work in explained variance, fairness, and runtime.  ...  The incorporation of MMD naturally leads to an exact and tractable mathematical formulation of fairness with good statistical properties.  ...  Figure 2 plots the explained variance and fairness metric values. Observe how MBF-PCA achieves better explained variance, while achieving similar level of fairness.  ... 
arXiv:2109.11196v4 fatcat:4jqmclomcnfx3o6pidbyrs33ie

Can Explainable AI Explain Unfairness? A Framework for Evaluating Explainable AI [article]

Kiana Alikhademi, Brianna Richardson, Emma Drobina, Juan E. Gilbert
2021 arXiv   pre-print
In this paper, we created a framework for evaluating explainable AI tools with respect to their capabilities for detecting and addressing issues of bias and fairness as well as their capacity to communicate  ...  In response, explainable artificial intelligence (XAI) tools that analyze the inner workings of a model have been created.  ...  For Random Forest, additional processing would definitely be needed to identify issues of fairness.  ... 
arXiv:2106.07483v1 fatcat:6kzy4k4znzffjkunc52n3lhlzu

Machine Learning – The Results Are Not the only Thing that Matters! What About Security, Explainability and Fairness? [chapter]

Michał Choraś, Marek Pawlicki, Damian Puchalski, Rafał Kozik
2020 Lecture Notes in Computer Science  
The aspects that can hinder practical and trustful ML and AI are: lack of security of ML algorithms as well as lack of fairness and explainability.  ...  However, this commonly used definition is too abstract to reach a consensus on the mathematical formulations of fairness.  ...  In its simplest form, the definition of explainability refers to an attempt to provide insights into the predictor's behavior [34] .  ... 
doi:10.1007/978-3-030-50423-6_46 fatcat:4r2tbrsc7zh2xc3svsp2wtnds4

DOES FAIR VALUE REPRESENT A CONCERN FOR ROMANIAN RESEARCHERS?

Jurcau Anca-Sabina, Andreicovici Ionela-Irina
2010 Annals of the University of Oradea: Economic Science  
This article is a literature review of the economic Romanian journals recognize by CNCSIS in the field of "fair value".  ...  In the actual economic context, the fair value concept is of high interest .We tried to see if the concept is only talk about, or if research in Romania has been actually done on this theme.  ...  IASB gives the following definition for fair value: Fair value is the price that would be received to sell an asset or paid to transfer a liability in an orderly transaction between market participants  ... 
doaj:ccf22c6f6ef741748b3e442fe1e7a61f fatcat:urvja7bgvvbafjctbuuotgswim

Fairness-Aware Explainable Recommendation over Knowledge Graphs [article]

Zuohui Fu, Yikun Xian, Ruoyuan Gao, Jieyu Zhao, Qiaoying Huang, Yingqiang Ge, Shuyuan Xu, Shijie Geng, Chirag Shah, Yongfeng Zhang, Gerard de Melo
2020 arXiv   pre-print
We propose a fairness constrained approach via heuristic re-ranking to mitigate this unfairness problem in the context of explainable recommendation over knowledge graphs.  ...  There has been growing attention on fairness considerations recently, especially in the context of intelligent decision making systems.  ...  Definition 5.5.  ... 
arXiv:2006.02046v2 fatcat:xvqm5qy55bcmzdtu35ep7l5kqm

Facing the Challenges of Developing Fair Risk Scoring Models

Gero Szepannek, Karsten Lübke
2021 Frontiers in Artificial Intelligence  
A definition of counterfactual fairness is given together with an algorithm that results in a fair scoring model.  ...  In addition, the challenge in explaining the resulting scoring model and the associated fairness implications to users is discussed.  ...  Section 5) and thus fulfills the definition of fairness through unawareness.  ... 
doi:10.3389/frai.2021.681915 pmid:34723172 pmcid:PMC8552888 fatcat:tljbusl7gnggrf3suhldw27c6u

Book Review

Adriaan Soetevent
2007 De Economist  
I however believe that the Fehr-Schmidt model with context-dependent tastes for fairness might explain this observation as well.  ...  Several aspects of the definition deserve explanation.  ... 
doi:10.1007/s10645-006-9047-5 fatcat:dxiqnhvxmvf2jkroqyqjbjsi24
« Previous Showing results 1 — 15 out of 623,075 results