Ethical and responsible decision making

Study how deep probabilistic models can be used for responsible decision making (i.e., make machines understand the consequences of their actions)
Description of the Project: 

Responsible AI, and ethical decision making are major concerns in AI. While definitions and ideas differ on how to capture these notions, it is widely agreed that causality will play a major role. In our ongoing work, e.g. Responsible AI, and ethical decision making are major concerns in AI. While definitions and ideas differ on how to capture these notions, it is widely agreed that causality will play a major role. In ongoing work, e.g. https://arxiv.org/pdf/1810.03736.pdf We have studied how the moral contexts of problems can be learned from data (e.g., for self-driving cars in the so-called trolley problem situation, in lung cancer staging) and the main concern now is to see how this can realized in a real-time interactive setting, e.g., as a robot navigates a complex world. Extensions to multi-agent settings are also possible. 

Resources required: 
High-throughput computing for simulations
Project number: 
300003
First Supervisor: 
University: 
University of Edinburgh
First supervisor university: 
University of Edinburgh
Essential skills and knowledge: 
Strong programming skills; grasp of probability, statistics; ability to work independently; interest in causality