29–30 Oct 2018
Hotel Mercure Budapest
Europe/Budapest timezone

Towards using ML in critical applications

30 Oct 2018, 17:20
25m
Mátyás Hall (Groundfloor) (Hotel Mercure Budapest)

Mátyás Hall (Groundfloor)

Hotel Mercure Budapest

Krisztina körút 41-43. 1013 Budapest Hungary
Lecture

Speaker

Andras Pataricza (Budapest University of Technology and Economics)

Description

Machine Learning provides highly efficient solutions for complex problems. However, the "black-box" or at most grey-box nature of the technology prohibits its use in many critical applications necessitating a throughgoing justification for the correctness of the results delivered.
One rapidly evolving approach is xAI (eXplainable AI) targeting the simultaneous delivery of a result and arguments for its integrity.
An alternative solution is to reuse the rich repertoire of measures collected in the field of fault-tolerant computing. One of the core problems addressed here is to build high-assurance solutions out of not entirely reliable services by using fault-detecting wrappers and redundancy scheme.
The presentation gives an overview of the synergy of AI and FT measures with an outlook to the integration of future xAI based solutions.

Primary author

Andras Pataricza (Budapest University of Technology and Economics)

Presentation materials

There are no materials yet.