50,825 Hits in 5.0 sec

Exploring Explainability: A Definition, a Model, and a Knowledge Catalogue [article]

Larissa Chazette and Wasja Brunotte and Timo Speith
2021 arXiv   pre-print
In this work, we bridge this gap by proposing a definition, a model, and a catalogue for explainability.  ...  Nevertheless, explainability is currently under-researched in the domain of requirements engineering and there is a lack of conceptual models and knowledge catalogues that support the requirements engineering  ...  A MODEL OF EXPLAINABILITY Models and catalogues compile knowledge about quality aspects and help to better visualize their possible impact on a system.  ... 
arXiv:2108.03012v1 fatcat:nmmqg4j2ebgldlpp3l4hiie27e

Supplementary Material for Research Paper "Exploring Explainability: A Definition, a Model, and a Knowledge Catalogue"

Larissa Chazette, Wasja Brunotte, Timo Speith
2021 Zenodo  
This is the supplementary material for the research paper Exploring Explainability: A Definition, a Model, and a Knowledge Catalogue accepted at the IEEE 29th Requirements Engineering Conference.  ...  . – and our workshops can be found here.  ...  ABOUT This is the supplementary material for the research paper "Exploring Explainability: A Definition, a Model, and a Knowledge Catalogue" accepted at the IEEE 29th Requirements Engineering Conference  ... 
doi:10.5281/zenodo.5114922 fatcat:4os3nvqzlvek5kgnyoacj2khxm

ENCODE explained

Joseph R. Ecker, Wendy A. Bickmore, Inês Barroso, Jonathan K. Pritchard, Yoav Gilad, Eran Segal
2012 Nature  
These findings force a rethink of the definition of a gene and of the minimum unit of heredity.  ...  explored.  ... 
doi:10.1038/489052a pmid:22955614 fatcat:nhmox6d6dnbnvdpdypupjkuqvi

On Explaining Everything

Diana Taschetto
2019 Metatheoria  
On this basis, the questions many-worlds models in Cosmology attempt to solve turn out to be a non-starter because their presupposed metaphysical grounding is ill-founded.  ...  This work explores foundational issues related to many-worlds theories in Cosmology.  ...  This work undertakes a systematic philosophical exploration and analysis of the latent assumptions responsible for the apparent reliability of manyworlds models in Cosmology.  ... 
doi:10.48160/18532330me9.236 fatcat:nrwbwm3qvndjfg2zflv6ypg6hy

Evaluating Explainability Methods Intended for Multiple Stakeholders

Kyle Martin, Anne Liret, Nirmalie Wiratunga, Gilbert Owusu, Mathias Kern
2021 Künstliche Intelligenz  
In this paper we present an explainability framework formed of a catalogue of explanation methods, and designed to integrate with a range of projects within a telecommunications organisation.  ...  We also present and investigate two metrics designed to model the quality of explanations - Meet-In-The-Middle (MITM) and Trust-Your-Neighbours (TYN).  ...  It achieves this by incorporating a catalogue of explainability techniques to provide transparency around system decision-making, and improve user understanding of the source data.  ... 
doi:10.1007/s13218-020-00702-6 fatcat:3xlwwynd6vee3dt2xwdr5tbypu

Fawcett, Peter. Translation and Language. Linguistic Theories Explained

Sara Oliveira
1999 Cadernos de Tradução  
These differences between languages lead to the creation of "a catalogue of translation techniques" and this is the topic of Chapter 4.  ...  Two are specially discussed: the first, based on methods of psychological investigation, is concerned with a model that attempts to explain how people's minds handle the process of translating.  ... 
doi:10.5007/5560 doaj:5f3f42e603b14403bccf1549eb4b9454 fatcat:i57wonbofbbsvowomalrioxjti

Who is this Explanation for? Human Intelligence and Knowledge Graphs for eXplainable AI [article]

Irene Celino
2020 arXiv   pre-print
Indeed, we call for a better interplay between Knowledge Representation and Reasoning, Social Sciences, Human Computation and Human-Machine Cooperation research -- as already explored in other AI branches  ...  eXplainable AI focuses on generating explanations for the output of an AI algorithm to a user, usually a decision-maker.  ...  We would like to thank Gloria Re Calegari and Ilaria Tiddi for their feedback and revision on this chapter.  ... 
arXiv:2005.13275v1 fatcat:nmmv6loaebfrfjcg5sv4pwar6m

Metrics for Explainable AI: Challenges and Prospects [article]

Robert R. Hoffman, Shane T. Mueller, Gary Klein, Jordan Litman
2019 arXiv   pre-print
The question addressed in this paper is: If we present to a user an AI system that explains how it works, how do we know whether the explanation works and the user has achieved a pragmatic understanding  ...  reliance on the AI are appropriate, and finally, (6) how the human-XAI work system performs.  ...  User models might consist of formalisms, such as production rules and semantic networks, which may represent a person's preferences and emulate some aspects of his or her knowledge and reasoning about  ... 
arXiv:1812.04608v2 fatcat:5uws33nmkrbxlltopncbvmzuke

A Survey on Explainable Artificial Intelligence (XAI): Towards Medical XAI [article]

Erico Tjoa, Cuntai Guan
2020 arXiv   pre-print
We provide a review on interpretabilities suggested by different research works and categorize them.  ...  will be born with more considerations for medical practices, and (3) initiatives to push forward data-based, mathematically- and technically-grounded medical education are encouraged.  ...  The program is the collaboration between Alibaba and Nanyang Technological university, Singapore.  ... 
arXiv:1907.07374v5 fatcat:ssup2eanlvertbcztuovdakykq

Explaining the rank order of invasive plants by stakeholder groups

Julia Touza, Alicia Pérez-Alonso, María L. Chas-Amil, Katharina Dehnen-Schmutz
2014 Ecological Economics  
Data were collected in Galicia, Spain, where a catalogue of prohibited entry and trade of invasive species is currently under debate.  ...  The influence these aspects have in the selection of top-ranked invaders varies across different stakeholder groups and with stakeholders' level of knowledge, awareness and attitudes towards different  ...  A. Pérez-Alonso acknowledges financial support from the Xunta de Galicia under project 10PXIB300141PR. Our gratitude goes out to  ... 
doi:10.1016/j.ecolecon.2014.06.019 fatcat:toiax55hcrexjpaomfz7fi6h2q

Explaining Police Bias

Michael R. Smith, Geoffrey P. Alpert
2007 Criminal Justice and Behavior  
This article proposes a theory of individual police behavior that is grounded in socialpsychological research on stereotype formation and that assumes a nonmotivational but biased response to minority  ...  After specifying the theory, the article presents a research agenda for empirically testing and verifying its propositions.  ...  Although it is a relatively small unit, its officers made more than 10% of the 174,919 stops catalogued and analyzed by the researchers who conducted the NYPD study.  ... 
doi:10.1177/0093854807304484 fatcat:jq2angv72nb5fiobomegypbxgq

A Framework for Exploring Digital Business Ecosystems

Kari Korpela, Usva Kuusiholma, Ossi Taipale, Jukka Hallikas
2013 2013 46th Hawaii International Conference on System Sciences  
This framework serves as a structure for exploring the value network and the enterprise as part of a digital business ecosystem.  ...  Digital business ecosystems are becoming an increasingly popular concept for modeling and building distributed systems in heterogeneous, decentralized and open environments.  ...  The definition of value activity elements has been explained and summarized in Table 2 .  ... 
doi:10.1109/hicss.2013.37 dblp:conf/hicss/KorpelaKTH13 fatcat:srbk4xy73rfpjpnkntpsnn4oqm

Exploring digitalisation at IKEA

Johan Hagberg, Anna Jonsson
2022 International Journal of Retail & Distribution Management  
retail giant, IKEA conducted with semi-structured interviews, participant observations and document analyses.FindingsIn the exploration phase of digitalisation, three major activities – interpreting,  ...  interrelating and integrating – illuminate how the exploration process can be organised in practice.Originality/valueAlthough digitalisation ranks amongst the most significant ongoing transformations in  ...  To the best of our knowledge, there is a dearth of research focussing specifically on the exploration phase and how it develops in practice.  ... 
doi:10.1108/ijrdm-12-2020-0510 fatcat:bm2xalwyxnajpnmhnjjj7tsabq

Explainable Artificial Intelligence for Developing Smart Cities Solutions

Dhavalkumar Thakker, Bhupesh Kumar Mishra, Amr Abdullatif, Suvodeep Mazumdar, Sydney Simpson
2020 Smart Cities  
In this work, we survey the concept of 'explainable deep learning' as a subset of the 'explainable AI' problem and propose a new solution using Semantic Web technologies, demonstrated with a smart cities  ...  It also has the distinct advantage of integrating experts' knowledge on defining the decision-making rules to represent the complex circumstances and using such knowledge to explain the results.  ...  Authors would like to thank the five experts from Bradford City Council who took part in the knowledge elicitation and evaluation process.  ... 
doi:10.3390/smartcities3040065 fatcat:up6gewcvzzhmfpcayynixpbao4

A New Approach for Explainable Multiple Organ Annotation with Few Data [article]

Régis Pierrard, Céline Hudelot
2019 arXiv   pre-print
Despite the recent successes of deep learning, such models are still far from some human abilities like learning from few examples, reasoning and explaining decisions.  ...  Given a catalogue of relations, it efficiently induces the most relevant relations and combines them for building constraints in order to both solve the organ annotation task and generate explanations.  ...  What makes a good explanation ultimately depends on the knowledge and expectation of the end-user.  ... 
arXiv:1912.12932v1 fatcat:3gisx3dnwbcxrcrnz45nq75jie
« Previous Showing results 1 — 15 out of 50,825 results