Raising Ethical Machines: Bottom-Up Methods to Implementing Machine Ethics

Raising Ethical Machines: Bottom-Up Methods to Implementing Machine Ethics

Marten H. L. Kaas
ISBN13: 9781799848943|ISBN10: 1799848949|ISBN13 Softcover: 9781799867982|EISBN13: 9781799848950
DOI: 10.4018/978-1-7998-4894-3.ch004
Cite Chapter Cite Chapter

MLA

Kaas, Marten H. L. "Raising Ethical Machines: Bottom-Up Methods to Implementing Machine Ethics." Machine Law, Ethics, and Morality in the Age of Artificial Intelligence, edited by Steven John Thompson, IGI Global, 2021, pp. 47-68. https://doi.org/10.4018/978-1-7998-4894-3.ch004

APA

Kaas, M. H. (2021). Raising Ethical Machines: Bottom-Up Methods to Implementing Machine Ethics. In S. Thompson (Ed.), Machine Law, Ethics, and Morality in the Age of Artificial Intelligence (pp. 47-68). IGI Global. https://doi.org/10.4018/978-1-7998-4894-3.ch004

Chicago

Kaas, Marten H. L. "Raising Ethical Machines: Bottom-Up Methods to Implementing Machine Ethics." In Machine Law, Ethics, and Morality in the Age of Artificial Intelligence, edited by Steven John Thompson, 47-68. Hershey, PA: IGI Global, 2021. https://doi.org/10.4018/978-1-7998-4894-3.ch004

Export Reference

Mendeley
Favorite

Abstract

The ethical decision-making and behaviour of artificially intelligent systems is increasingly important given the prevalence of these systems and the impact they can have on human well-being. Many current approaches to implementing machine ethics utilize top-down approaches, that is, ensuring the ethical decision-making and behaviour of an agent via its adherence to explicitly defined ethical rules or principles. Despite the attractiveness of this approach, this chapter explores how all top-down approaches to implementing machine ethics are fundamentally limited and how bottom-up approaches, in particular, reinforcement learning methods, are not beset by the same problems as top-down approaches. Bottom-up approaches possess significant advantages that make them better suited for implementing machine ethics.

Request Access

You do not own this content. Please login to recommend this title to your institution's librarian or purchase it from the IGI Global bookstore.