The objective of this presentation is to introduce and demonstrate the Zenoh-Flow framework as a solution to the challenges of developing and managing machine learning (ML) applications in the decentralized Cloud-to-Things continuum.
The presentation will highlight the following points:
- The complexity involved in developing and managing ML applications in the decentralized IoT ecosystem.
- Introduction of Zenoh-Flow as a dataflow programming framework that simplifies the implementation of End-to-End ML pipelines in a fully decentralized manner, abstracting communication aspects.
- Showcase of a real-world use case demonstrating the effectiveness of Zenoh-Flow in improving overall performance and reducing network usage compared to the original implementation.
- Highlighting the inherent benefits of Zenoh-Flow, including its contribution to developing efficient and scalable ML applications in the decentralized IoT ecosystem.
- The potential impact of Zenoh-Flow in enabling the next-generation ML-powered applications in the IoT domain.
- Encouraging further exploration and adoption of Zenoh-Flow as a valuable tool for developers and researchers working in the IoT and ML fields.
Overall, the presentation aims to inform the audience about the challenges faced in developing ML applications in the IoT domain and how Zenoh-Flow addresses these challenges, leading to improved performance and scalability.
Objective of the presentation:
The objective of this presentation is to introduce and demonstrate the Zenoh-Flow framework as a solution to the challenges of developing and managing machine learning (ML) applications in the decentralized Cloud-to-Things continuum.
Attendee pre-requisites - If none, enter "N/A":
N/A