Conference

The »Embedded World Exhibition and Conference« is the industry meeting place for leading experts from the embedded community. It offers an insight into the entire world of embedded systems: from components and modules to operating systems, hardware and software design, M2M communication and services.

A team from the »Analytics and Computing« division and the Rhineland-Palatinate University of Technology Kaiserslautern-Landau (RPTU) from the »Design of Microelectronic Systems (EMS)« department presents our AI system »Neural Architecture Search for Embedded Applications (NASE)« at the Fraunhofer-Gesellschaft's joint booth.

Neural Architecture Search: The Connection Between Application and Hardware

Cloud-edge and embedded solutions increasingly adopt AI as a core component to make services more reliable and improve the user experience. But bringing AI towards the edge is difficult, as the AI models need optimization for the executing hardware platform. Common design processes do not scale, as adjusting models manually results in long development times.

Recently, agentic systems have demonstrated for many programming and development tasks that development time can be reduced significantly by the automation of design and testing cycles. Agentic AI systems can solve complex tasks reliably by interacting with external tools and testing systems. At the same time, AI agents interact with the user in natural language and explain the results in an easy to understand way. Even non-experts can utilize such systems to solve their problems, making complex technologies more accessible to everyone.

NASE is an agentic AI system that optimizes the execution of AI models for various edge and embedded platforms by using hardware awareness. It helps the user to specify optimization criteria and to identify the best models for the application and platform. NASE can directly design, deploy and test models on the target hardware, which allows it to verify model execution performance with real measurements. Development times can go down from month to weeks and the quality of the resulting models beats manual design.