The webinar is organised by the SPACE CoE and NCC Czechia.
Annotation
ONNX (Open Neural Network Exchange) is an open-source framework designed to enable interoperability of machine learning models across various AI tools and platforms supported by many key players in the field. It provides a standard format for representing machine learning and deep learning models. This simplifies deployment and enhances reproducibility of experiments. ONNX supports a wide range of operations and architectures, making it versatile for both industry and academia. By standardizing model representation and providing robust optimization and deployment tools, ONNX lowers barriers to advanced AI research and application, making cutting-edge technology more accessible to the scientific community. ONNX is particularly valuable for basic science because it promotes collaborative research by offering a common language for different tools. It accelerates experimentation, enabling rapid testing and validation of models. Compatibility with various hardware accelerators ensures efficient model execution. ONNXRuntime optimizes model performance, crucial for deployment in resource-constrained environments.
The seminar will also provide a status on the considerations for the use of ONNX in SPACE.
Benefits for the attendees, what will they learn
In a talk about ONNX and the LF AI & Data (Linux Foundation AI & Data) initiative, attendees will learn about the key concepts, technologies, and opportunities related to ONNX as well as the broader AI and data ecosystem supported by the Linux Foundation. In addition, users will be given points of contact if they plan to use onnx in their own field.
Language
English
Level
Beginner
Prerequisites
Interest in open standards and the background of open source communities and opportunities to participate in them.
Tutor
Dr. Andreas Fehlner studied physics at the University of Regensburg and obtained his Ph.D. in biomedical imaging in Berlin. He works as project manager and software engineer for machine learning in pre-development with a focus on transferring ideas in the field of AI to working products at a mechanical engineering company in industry. In his spare time, he supports the Heidelberg Institute for Theoretical Studies to pursue new and exciting scientific questions. He is passionate about the goals of Open Source for AI. As a former elected member of the ONNX (Open Neural Network Exchange) Steering Committee, he is committed to establishing this standard.
Acknowledgements

This work was supported by the SPACE project under grant agreement No 101093441. The project is supported by the European High-Performance Computing Joint Undertaking and its members (including top-up funding by the Ministry of Education of the Czech Republic ID: MC2304).
This project has received funding from the European High-Performance Computing Joint Undertaking (JU) under grant agreement No 101101903. The JU receives support from the Digital Europe Programme and Germany, Bulgaria, Austria, Croatia, Cyprus, Czech Republic, Denmark, Estonia, Finland, Greece, Hungary, Ireland, Italy, Lithuania, Latvia, Poland, Portugal, Romania, Slovenia, Spain, Sweden, France, Netherlands, Belgium, Luxembourg, Slovakia, Norway, Türkiye, Republic of North Macedonia, Iceland, Montenegro, Serbia. This project has received funding from the Ministry of Education, Youth and Sports of the Czech Republic.

This course was supported by the Ministry of Education, Youth and Sports of the Czech Republic through the e-INFRA CZ (ID:90254).
Dr. Andreas Fehlner would like to thank the ONNX community, which has given him the confidence to participate more intensively and has made me realize the importance of open standards.