{"id":2071,"date":"2025-08-15T11:28:26","date_gmt":"2025-08-15T09:28:26","guid":{"rendered":"https:\/\/www.esi.fau.de\/?page_id=2071"},"modified":"2025-10-06T09:58:16","modified_gmt":"2025-10-06T07:58:16","slug":"et19","status":"publish","type":"page","link":"https:\/\/www.esi.fau.de\/en\/et19\/","title":{"rendered":"19. Embedded Talk: Deep Learning on Narrow Resources"},"content":{"rendered":"

The 19th Embedded Talk <\/strong>will take place on October 10th, 2025<\/strong>, 1:00 pm<\/strong> on the premises of Friedrich-Alexander-Universit\u00e4t Erlangen-N\u00fcrnberg at Erlangen S\u00fcdgel\u00e4nde (Cauerstr. 11, Erlangen, lecture hall H12). Immerse yourself into the world of \u00a0Embedded AI<\/strong> and find out more about the latest developments in this field, especially about Deep Learning on devices with restricted resources.<\/p>\n

The research focus \u201cEmbedded AI\u201d deals with the application of artificial intelligence for the design of (embedded) electronic systems as well as the design of intelligent electronic systems, in particular autonomous systems. However, lightweight implementations of such embedded autonomous systems present researchers and developers with major challenges that have not yet been adequately solved in terms of data volumes, storage and processing performance, as well as the correctness, safety and security of such intelligent systems.<\/p>\n

Due to the high costs, size and relatively high energy consumption, known techniques for implementing machine learning algorithms cannot therefore be used in everyday objects (Internet of Things, IoT), e.g. an intelligent rolling bearing, an adaptive valve or a hearing aid that adapts itself to the wearer. It is important to break new ground here so that machine learning is also possible on small, embedded systems. In the area of analysis and verification, there is also a considerable need for interdisciplinary research to investigate the role and integration of machine learning methods in established methods of signal processing, control engineering and system design. Another branch of research is aimed at assuring provable quality criteria for properties such as robustness, fault tolerance, safety and real-time of learning systems that cannot be statically verified. Guaranteeing the privacy of data and models is also a major challenge for numerous fields of application. In design automation, there are also fundamental questions regarding the support and integration of machine learning (ML) and symbolic AI methods, especially for IoT devices.<\/p>\n

The Embedded Talk is an established series of events that is an ideal information and communication forum to promote regular exchange between experts from science and industry.<\/p>\n

Program<\/h2>\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n
13:00:<\/td>\nWelcome Remarks<\/td>\n<\/tr>\n
<\/td>\nProf. Dr.-Ing. J\u00fcrgen Teich, Speaker FAU ESI, FAU Erlangen-N\u00fcrnberg<\/td>\n<\/tr>\n
13:15:<\/td>\nKeynote: Resource-Aware Machine Learning for Cyber-Physical Systems<\/td>\n<\/tr>\n
<\/td>\nProf. Dr. Jian-Jia Chen, TU Dortmund \/ Lamarr-Institute for Machine Learning and Artificial Intelligence<\/td>\n<\/tr>\n
14:00:<\/td>\nOn-Device Training of Deep Neural Networks on Cortex-M Microcontrollers<\/span>AI<\/td>\n<\/tr>\n
<\/td>\nMark Deutel, Researcher, Fraunhofer IIS \/ FAU Erlangen-N\u00fcrnberg<\/span><\/td>\n<\/tr>\n
14:45:<\/span><\/td>\nCoffee Break<\/td>\n<\/tr>\n
<\/td>\n<\/td>\n<\/tr>\n
15:15: <\/span><\/td>\nReal-World Challenges of Deploying Embedded<\/td>\n<\/tr>\n
\u00a0<\/span><\/td>\nJan Seyler , Festo SE & Co. KG<\/span><\/td>\n<\/tr>\n
16:00:<\/span><\/td>\nPanel Discussion<\/td>\n<\/tr>\n
\u00a0<\/span><\/td>\n\u00a0
\n<\/span><\/td>\n<\/tr>\n
16:45<\/span><\/td>\nPoster-Session, Get-Together and Networking<\/span><\/td>\n<\/tr>\n
\u00a0<\/span><\/td>\n<\/td>\n<\/tr>\n
~17:30<\/span><\/td>\nEnd of the Event<\/td>\n<\/tr>\n<\/tbody>\n<\/table>\n

Note: This Embedded Talk will be held in English<\/strong>.<\/p>\n

Venue<\/h2>\n

Campus S\u00fcdgel\u00e4nde
\nFriedrich-Alexander-Universit\u00e4t Erlangen-N\u00fcrnberg
\nEmmy-Noether-H\u00f6rsaal (H12)
\nCauerstra\u00dfe 11, 91058 Erlangen<\/p>\n

Registration<\/h2>\n

Register here<\/a> (free<\/strong> of charge)<\/p>\n

Flyer<\/h2>\n

You can download a flyer (PDF) of the event<\/a> here.<\/p>\n

\n

Dr.-Ing.<\/span> Torsten<\/span> Klie<\/span><\/span><\/span><\/a><\/h3>
Gesch\u00e4ftsf\u00fchrer<\/span>

FAU Research Center Embedded Systems Initiative (ESI)<\/span>
Gesch\u00e4ftsstelle<\/span>
<\/p>