Expert in the loop: Human-Machine Interaction to Build Safe AI-Based Systems
Date:
This talk presents research work on the development of reliable learning frameworks addressing the problems of data complexity and low error tolerance in high-risk applications.
I discuss Interactive Machine Learning as a way to optimize the learning process of AI systems in the presence of complex data. I also present on-going work on performance assessment in the absence of ground truth, and on how to explit this measurement to provide evidence for informed decision-making to an expert.