A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2019; you can also visit the original URL.
The file type is application/pdf.
Filters
Extensionally defining principles and cases in ethics: An AI model
2003
Artificial Intelligence
Preserved Fulltext
This paper discusses research in which the following hypothesis was empirically tested: extensionally defined principles, as well as cited past cases, can help in predicting the principles and cases that ...
To investigate this phenomenon computationally, a large set of professional ethics cases was analyzed and a computational model called SIROCCO, a system for retrieving principles and past cases, was constructed ...
I would also like to thank the anonymous reviewers of the paper and the editors of this special edition of the AI Journal, who provided many helpful suggestions and comments. ...
doi:10.1016/s0004-3702(03)00135-8
fatcat:gdn7pzbhufgxtjav23kjm77zdi
Extensionally Defining Principles and Cases in Ethics: an AI model
2018
Preserved Fulltext
A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2020; you can also visit the original URL.
The file type is application/pdf.
This paper discusses research in which the following hypothesis was empirically tested: extensionally defined principles, as well as cited past cases, can help in predicting the principles and cases that ...
To investigate this phenomenon computationally, a large set of professional ethics cases was analyzed and a computational model called SIROCCO, a system for retrieving principles and past cases, was constructed ...
In particular, (1) the concept and use of operationalization of abstract principles in an ill-defined domain and (2) the example the SIROCCO project provides of how an AI model and methods can be used ...
doi:10.1184/r1/6470063
fatcat:igzgillkxzforjdk2g26wy5i7y
Philosophical Specification of Empathetic Ethical Artificial Intelligence
[article]
2021
arXiv
pre-print
Preserved Fulltext
A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2021; you can also visit the original URL.
The file type is application/pdf.
In order to construct an ethical artificial intelligence (AI) two complex problems must be overcome. Firstly, humans do not consistently agree on what is or is not ethical. ...
An ethical AI must be capable of inferring unspoken rules, interpreting nuance and context, possess and be able to infer intent, and explain not just its actions but its intent. ...
ACKNOWLEDGEMENTS We would like to acknowledge and thank the reviewers for their thoughtful and detailed feedback, which improved this paper substantially. ...
arXiv:2107.10715v1
fatcat:ek7h6llu6zfzrnkilg2pzv6hj4
Particularism and Generalism: How AI can Help us to Better Understand Moral Cognition
[chapter]
2020
Machine Ethics and Robot Ethics
Preserved Fulltext
A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2017; you can also visit the original URL.
The file type is application/pdf.
Neural network models of moral case classification are presented, and the contrast case method for testing and revising case classifications is considered. ...
Particularism and Generalism refer to families of attitudes towards moral principles. ...
It is in considering how to revise cases that principles (whether they are called contributory, open textured, extensionally defined, et cetera) will likely loom large. ...
doi:10.4324/9781003074991-26
fatcat:b3lmwrljkzeddezurskdkfkheq
Automated argument adjudication to solve ethical problems in multi-agent environments
2021
Paladyn: Journal of Behavioral Robotics
Preserved Fulltext
A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2021; you can also visit the original URL.
The file type is application/pdf.
content, and (ii) must solve an ethical problem on the basis of what it has received. ...
ethical principles) recommendation based upon such adjudication. ...
(with a special thanks here to the wise guidance and inspiration of Michael Qin), and for their past support of our R&D in robot/machine ethics (primarily under a MURI to advance the science and engineering ...
doi:10.1515/pjbr-2021-0009
fatcat:532cmp5urnf4vmrst2kcttpwty
Ethics and Good Practice in Computational Paralinguistics
2020
IEEE Transactions on Affective Computing
Preserved Fulltext
A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2020; you can also visit the original URL.
The file type is application/pdf.
In this article, we try to set the scene by (1) giving a short overview of ethics and privacy, (2) describing the field of Computational Paralinguistics, its history and exemplary use cases, as well as ...
With the advent of 'heavy Artificial Intelligence' -big data, deep learning, and ubiquitous use of the internet, ethical considerations are widely dealt with in public discussions and governmental bodies ...
In [21] , Jobin et al. find a convergence around ethical principles in Artificial Intelligence (AI) ethics guidelines, however, with "substantive divergence" as far as interpretation and implementation ...
doi:10.1109/taffc.2020.3021015
fatcat:gvbk6whi6fd53j24ogf7wtpo2i
Computational Models of Ethical Reasoning: Challenges, Initial Steps, and Future Directions
2006
IEEE Intelligent Systems
Preserved Fulltext
A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2007; you can also visit the original URL.
The file type is application/pdf.
The other program, SIROCCO, accepts a single ethical dilemma and retrieves other cases and ethical principles that might be relevant. Neither program was designed to reach an ethical decision. ...
Here, I briefly describe a few of these programs and discuss in detail two programs that I developed, both of which employ techniques from the area of AI known as case-based reasoning and implement aspects ...
Acknowledgments Kevin Ashley contributed greatly to the ideas behind both Truth-Teller and SIROCCO. ...
doi:10.1109/mis.2006.67
fatcat:zfeaoe4aibea7gglyoy6mmccje
Ethical Regulation of Robots Must Be Embedded in Their Operating Systems
[chapter]
2015
A Construction Manual for Robots' Ethical Systems
Preserved Fulltext
A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2019; you can also visit the original URL.
The file type is application/pdf.
Ob(p) Note that no global ethical principles are enforced. ...
Robotic Substrate Ethical Substrate Future 1 Future 2 Only "obviously" dangerous higher-level AI modules have ethical safeguards.
} Higher-level cognitive and AI modules All higher-level AI modules interact ...
Figure 4 : DC EC * Syntax and Rules of Inference The final layer in our hierarchy is built upon an even more expressive logic: DC EC * CL . ...
doi:10.1007/978-3-319-21548-8_5
dblp:series/cogtech/GovindarajuluB15
fatcat:qroxahdukna4bbtgrbtlshkivy
Consequentialize This
2011
Ethics: An International Journal of Social, Political, and Legal Philosophy
Preserved Fulltext
A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2019; you can also visit the original URL.
The file type is application/pdf.
Formal Model I begin by defining a simple formal model. The model will take entities of two sorts as primitives: possible worlds and agents. ...
The maximal elements in a set X, relative to an order ≤ , may be defined as follows:
Ethics July 2011 max (X ) p {x:x X and for all y, ≤ if y X, and x ≤ y then y ≤ x}. (See Sec. ...
Consider then 'satisficing utilitarianism', defined as follows: an alternative x is right iff the total well-being in x is at least as great as 0.8 times the total well-being in every alternative. ...
doi:10.1086/660696
fatcat:pde6sxbhpfeppn5brrsqyyuiby
MicroRNA-1 Accelerates the Shortening of Atrial Effective Refractory Period by Regulating KCNE1 and KCNB2 Expression: An Atrial Tachypacing Rabbit Model
2013
PLoS ONE
Preserved Fulltext
A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2017; you can also visit the original URL.
The file type is application/pdf.
The purpose of this study was to evaluate the effects of miR-1 on the atrial effective refractory period (AERP) in a right atrial tachypacing model and to elucidate the potential mechanisms. ...
The slowly activating delayed rectifier potassium current (IKs) and AERP in atrial cells were measured by whole cell patch clamp in vitro. ...
KCNB2 is expressed in the heart and affects cardiac K + currents [29] , but the extensional process remains unclear. ...
doi:10.1371/journal.pone.0085639
pmid:24386485
pmcid:PMC3875574
fatcat:rzcyvebmwbhmbkd3d6g42wq2qe
The Ethical Gravity Thesis: Marrian Levels and the Persistence of Bias in Automated Decision-making Systems
2021
Proceedings of the 2021 AAAI/ACM Conference on AI, Ethics, and Society
Preserved Fulltext
A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2021; you can also visit the original URL.
The file type is application/pdf.
Computers are used to make decisions in an increasing number of domains. There is widespread agreement that some of these uses are ethically problematic. ...
This paper expands and defends the Ethical Gravity Thesis: ethical problems that arise at higher levels of analysis of an automated decision-making system are inherited by lower levels of analysis. ...
In each case, however, we can view the functionally defined problem through a mathematical lens-and, indeed, we must do so if we are to program a computer to find the answer we seek. ...
doi:10.1145/3461702.3462606
fatcat:5gshrc6pr5chpefgcjya4zc6ta
Deontic Counteridenticals and the Design of Ethically Correct Intelligent Agents: First Steps
2016
European Conference on Artificial Intelligence
Preserved Fulltext
A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2022; you can also visit the original URL.
The file type is application/pdf.
We provide a propaedeutic discussion and demonstration of this design strategy (which is at odds with the strategy our own lab has heretofore followed in ethical control), one involving AAIAs in our lab ...
But counteridenticals of an "ethical" sort apparently haven't been analyzed to speak of, let alone formalized. ...
AI (e.g., see Bringsjord & Ferrucci 1998 , Bringsjord 2008b ) and its sister field computational cognitive modeling (e.g., see Bringsjord 2008a). ...
dblp:conf/ecai/BringsjordGP16
fatcat:a7h4tpv7mzhn5hoff3ykkux4du
Forthcoming Papers
2003
Artificial Intelligence
Preserved Fulltext
A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2019; you can also visit the original URL.
The file type is application/pdf.
Sartor, A model of legal reasoning with cases incorporating theories and values Reasoning with cases has been a primary focus of those working in AI and law who have attempted to model legal reasoning. ...
Law, learning and representation In machine learning terms, reasoning in legal cases can be compared to a lazy learning approach in which courts defer deciding how to generalize beyond the prior cases ...
McLaren, Extensionally defining principles and cases in ethics: An AI model Principles are abstract rules intended to guide decision-makers in making normative judgments in domains like the law, politics ...
doi:10.1016/s0004-3702(03)00158-9
fatcat:sze4uoaylzchzbn3lifjjfgtny
Ends to Means
2017
Journal of Ethics and Social Philosophy
Preserved Fulltext
A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2018; you can also visit the original URL.
The file type is application/pdf.
In short, an action is a means to an end insofar as it raises the probability of the end relative to the worst one could do. ...
This paper defends a probability-raising theory of what it is to be a means to an end, and how much reason transmits from an end to its means. ...
modeling reason transmission. ...
doi:10.26556/jesp.v12i1.207
fatcat:kmkio7bpencwtogqtafcwydubq
An AI investigation of citation's epistemological role
2001
Proceedings of the 8th international conference on Artificial intelligence and law - ICAIL '01
Preserved Fulltext
A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2006; you can also visit the original URL.
The file type is application/pdf.
This paper describes how we used an AI model for retrieving ethics cases to investigate empirically the epistemological contributions of a decision-makers' citing cases and code provisions in justifying ...
After investigating hundreds of professional ethics case opinions, we hypothesized that the decision-makers' explanations extensionally defined principles over time, in effect, operationalizing them. ...
Here an AI model enables us to do exactly that. ...
doi:10.1145/383535.383539
dblp:conf/icail/AshleyM01
fatcat:zju3xq2v4vev3lccm4jl2ebng4
« Previous
Showing results 1 — 15 out of 303 results