Tutor: Professor Antonis Kakas
🌍 www.cs.ucy.ac.cy/~antonis/
🏛 ️Department of Computer Science, University of Cyprus (CY)
✉ antonis<at>ucy.ac.cy
Short CV
Antonis C. Kakas is a Professor at the Department of Computer Science of the University of Cyprus. He obtained his Ph.D. in Theoretical Physics from Imperial College London in 1984. His interest in Computing and AI started in 1989 under the group of Professor Kowalski. Since then, his research has concentrated on computational logic in AI with particular interest in argumentation, abduction and induction and their application to machine learning and cognitive systems. Currently, he is working on the development of a new framework of Cognitive Programming as an environment for developing Human-centric AI systems that can be naturally used by developers and human users at large. In this context he has a keen interest in AI Ethics. He was the National Contact Point for Cyprus in the flagship EU project on AI, AI4EU. He has recently co-founded a start-up companyin Paris, called Argument Theory, which offers solutions to real-life application decision taking problems based on AI Argumentation Technology.
Tutorial Description
What is an appropriate logical foundation for ethical AI? This tutorial will present a philosophical discussion on this question and how this relates to two main requirements of AI Ethics: compliance or alignment to moral values and accountability through explainability. The emphasis of the tutorial will not be so much on morality itself, i.e., what are the moral values for AI Ethics, but on how systems would reason about morality and how their design would accommodate an ethical behaviour that adheres to moral values. Should systems be built with hard norms that are applied under strict logical reasoning or should they operate under a more flexible logical form of normative guidance? How can the later form be realized? Under which logical foundation?
After a short review of the logic of ethics in philosophy we will consider and address the following topics within the context of recent developments of AI:
- What is a good or acceptable ethical operation of a system?
- Perfection or Sensitivity to special cases and Adaptability.
- How are ethical norms formulated and represented within an AI system?
- Modal Logic vs Argumentation Logic
- Strict Norm Compliance or Normative Guidance?
- Absolute Compliance vs Flexible Leniency
- Optimal Rationality or Dialectic Rationality of satisficing sustainable decisions.
- One shot Ethics by Rational Design or Habitual & Continuous Ethicacy over operation.
- What is a good form of Ethical Data for Moral Machine Learning?
- How does logical explainability contribute to the ethicacy of AI systems?
- What are good quality ethical characteristics of explanations?
Intended Audience & Prerequisites
The tutorial is aimed at all AI researchers, junior or senior, who have an interest in the philosophical and logical underpinnings of AI Value Alignment and AI Ethics. There are no special prerequisites for following the tutorial.
Duration
The tutorial will take 3 hours including an open discussion session and a short break in the middle.