An approach to computing ethics

A team of an ethicist and computer scientists are making attempts to make ethics computable by employing an approach, M that employs machine learning to help determine the ethically correct action when different ethical duties give conflicting advice. This approach lends itself to machine implementation by giving the agent either a single principle or several principles to guide its actions, unlike other approaches that don't specify the correct action in an ethical dilemma. A good action-based ethical theory should have consistency and completeness that indicates how to act in any ethical dilemma. The approach to computing ethics is illustrated by MEDETHEX, a system that uses machine learning to resolve a biomedical ethical dilemma. The method adopted for the computation can help make a multiple prima facie duty theory and adopts John Rawl's reflective equilibrium approach to creating and refining ethical principles.