Saeed Bakhshi Germi
Safety in Artificial Intelligence
Artificial Intelligence (AI) - Machine Learning (ML) algorithms specifically - are increasingly being used in different aspects of our life like autonomous vehicles, power plants, medical robots and other systems. Most of the systems demand the concept of “safety” to be added when they are involved with ML due to the nature of it.
Safety can be defined in terms of risk, epistemic uncertainty, and the harm incurred by unwanted outcomes.
This Project aims to find different strategies for achieving safety in engineering that can be mapped to the machine learning context.