Neuro-symbolic Systems for Ethical AI: Challenges and Opportunities

Machine learning (ML) techniques have become pervasive across a range of different applications, and are now widely used in areas as disparate as recidivism prediction, consumer credit-risk analysis, and insurance pricing. Like- wise, in the physical world, ML models are critical components in autonomous agents such as robotic surgeons and self-driving cars. Among the many ethical dimensions that arise in the use of ML technology in such applications, analyzing morally permissible actions is both immediate and profound. For example, there is the potential for learned algorithms to become biased against certain groups. More generally, in so much that the decisions of ML models impact society, both virtually (e.g., denying a loan) and physically (e.g., driving into a pedestrian), notions of accountability, blame and responsibility need to be carefully considered. In this talk, we advocate for a two-pronged approach ethical decision-making enabled using rich models of autonomous agency: on the one hand, we need to draw on philosophical notions of such as beliefs, causes, effects and intentions, and on the other, we consider the problem of practical and effective knowledge acquisition and learning. This was a talk given at the Workshop on AI Vulnerabilities and their Societal Implications, 2024 -- https://www.technomoralfutures.uk/events-database/ai-vulnerabilities-and-their-societal-implications-workshop