The work “Integration and deployment of Model Serving Framework to serve machine learning models at production scale in easy way”, with the support of NEANIAS project, was presented.

• Authors: F. Caronte [1] R. Messineo [1] J. Kovacs [2] E. Sciacca [3]
• Affiliations: [1] ALTEC; [2] SZTAKI; [3] INAF

Abstract

With the help of machine learning systems, we can examine data, learn from that data and make decisions. Now machine learning projects have become more relevant to various use case, but too many models are difficult to manage. For this reason several MLOps tools were born. These tools are the main platforms, hosting the full machine learning process lifecycle, starting with data management and ending with model versioning and deployment.
NEANIAS (Novel EOSC Services for Emerging Atmosphere, Underwater & Space Challenges) is an ambitious project that comprehensively addresses the challenges set out in the ‘Roadmap for EOSC’ foreseen actions.
NEANIAS drives the co-design and delivery of innovative thematic services, derived from state-of-the-art research assets and practices in three major sectors: Underwater research, Atmospheric research and Space research.
The machine learning core services identified in the NEANIAS Project allow the scientists to define machine learning models and manage their lifecycle.

Acknowledgements

This work has been fully supported by NEANIAS, funded by the European Union's Horizon 2020 research and innovation program, under grant agreement No 863448.

Learn more at https://indico.ict.inaf.it/event/1692/contributions/11269/