Adrian Schwaiger of the Fraunhofer Institute for Cognitive Systems IKS will be presenting his new paper at the AI Safety Workshop on January 7, 2021. The workshops seeks to explore new ideas on safety engineering and puts the focus on strategic, ethical and policy aspects of safety-critical AI-based systems .Due to the current situation the workshop will take place virtually.

In their paper »Is Uncertainty Quantification in Deep Learning Sufficient for Out-of-Distribution Detection?« the IKS-researchers compare state-of-the-art uncertainty quantification methods for deep neural networks with respect to their ability to detect new inputs.

 

Talk at AI Safety Workshop
Adrian Schwaiger
»Is Uncertainty Quantification in Deep Learning Sufficient for Out-of-Distribution Detection?«
January 7, 2021
10.30 am UTC
virtual