M. Sc.
Research Engineer
Nicola Franco, a research scientist at Fraunhofer IKS since 2020, is currently pursuing his PhD at the Technical University of Munich, specializing in data analytics and machine learning. His research primarily revolves around enhancing the safety and reliability of AI systems, with a particular emphasis on adversarial robustness, formal verification of AI algorithms, and the emerging field of quantum AI. In 2023, he received a 'Best Paper Award' at the AI Safety Conference in Macao.
by Nicola Franco
Neural networks are not robust. The development of reliable predictors requires systematic methods to both assess their quality and to gain confidence in their correctness. Quantum computing can help here.
Quantum computing represents a frontier in computational technology, offering unparalleled potential for solving complex problems. However, this revolutionary field is not without its challenges. In this blog post, we will explore the vast potential of quantum optimization, identify the key challenges that lie ahead, and discuss strategies for navigating the path forward in this exciting domain.
Cyber-physical systems (CPS) integrate software algorithms and physical structures. To exceed the simple embedded systems of today, advances in CPS require several properties, particularly adaptability, resilience, and safety. Lean management of CPS with resilient architectures satisfies these requirements by combining data distribution with service-oriented structures. A practical use case: a moving robot in a warehouse.
