Description
Tutorials:
Introduction to the AI4EOSC platform (ca.10’)
Build AI application /service based on existing AI modules using the AI4EOSC platform (ca.25’)
Develop a new AI application / service with the AI4EOSC platform (ca.25’)
Please, follow Preparation Steps BEFORE the session!
Deploy your AI-based service for inference using the AI4EOSC platform (ca.25’)
Speakers:
Ignacio Heredia (CSIC), Khadijeh Alibabaei (KIT), Amanda Calatrava (UPV) (maybe: Valentin Kozlov (KIT))
Description:
The AI4EOSC delivers an enhanced set of advanced services for the development and serving of Artificial Intelligence (AI), Machine Learning (ML) and Deep Learning (DL) models and applications in the European Open Science Cloud (EOSC). The project builds its technology based on the results of the DEEP-Hybrid-DataCloud project and other previous ICT projects, where the partners have developed new innovative services to support machine learning over the cloud. In AI4EOSC, we evolve those services to better support the new challenges ahead when building distributed AI applications and improve scalability and performance for large-scale AI applications..In the hands-on workshop, the AI practitioners and all interested people will learn how the AI4EOSC/DEEP AI platform supports typical scenarios for AI-based applications and services: re-use of existing AI modules on the marketplace, AI model development from scratch and training, and model serving.
Acknowledgment: AI4EOSC receives funding from the European Union’s Horizon Europe 2022 research and innovation programme under agreement 101058593
Relevant links:
AI4EOSC project: https://ai4eosc.eu
AI4EOSC/DEEP platform documentation: https://docs.deep-hybrid-datacloud.eu
OSCAR framework for FaaS: https://docs.oscar.grycap.net/
Jupyter notebook repository (for the "Develop AI application" part): https://git.scc.kit.edu/m-team/ai/ai4eosc-egi23-tutorial
