Learning Tractable Probabilistic Models for Moral Responsibility and Blame
| Autor: | Lewis Hammond, Vaishak Belle |
|---|---|
| Jazyk: | angličtina |
| Rok vydání: | 2021 |
| Předmět: |
FOS: Computer and information sciences
Computer Science - Machine Learning Computer Science - Logic in Computer Science Computer Networks and Communications Computer science Computer Science - Artificial Intelligence media_common.quotation_subject Judgement 02 engineering and technology 050105 experimental psychology Machine Learning (cs.LG) Blame 0202 electrical engineering electronic engineering information engineering 0501 psychology and cognitive sciences Moral responsibility Learning for ethical reasoning media_common Teamwork Management science 05 social sciences Probabilistic logic Logic in Computer Science (cs.LO) Computer Science Applications Tractable probabilistic models Artificial Intelligence (cs.AI) 020201 artificial intelligence & image processing Information Systems |
| Zdroj: | Hammond, L & Belle, V 2021, ' Learning Tractable Probabilistic Models for Moral Responsibility and Blame ', Data Mining and Knowledge Discovery, vol. 35, no. 2, pp. 621-659 . https://doi.org/10.1007/s10618-020-00726-4 |
| DOI: | 10.1007/s10618-020-00726-4 |
| Popis: | Moral responsibility is a major concern in autonomous systems, with applications ranging from self-driving cars to kidney exchanges. Although there have been recent attempts to formalise responsibility and blame, among similar notions, the problem of learning within these formalisms has been unaddressed. From the viewpoint of such systems, the urgent questions are: (a) How can models of moral scenarios and blameworthiness be extracted and learnt automatically from data? (b) How can judgements be computed effectively and efficiently, given the split-second decision points faced by some systems? By building on constrained tractable probabilistic learning, we propose and implement a hybrid (between data-driven and rule-based methods) learning framework for inducing models of such scenarios automatically from data and reasoning tractably from them. We report on experiments that compare our system with human judgement in three illustrative domains: lung cancer staging, teamwork management, and trolley problems. Published in Data Mining and Knowledge Discovery (2021) |
| Databáze: | OpenAIRE |
| Externí odkaz: |
|