Synthesis
Synthesis is a cutting-edge framework designed to advance edge machine learning and federated learning. It combines sophisticated algorithms with user-friendly experiences to streamline model management, automate anomaly detection, and simplify connectivity.
Federated Learning
A revolutionary approach in machine learning where a model is trained across multiple decentralized edge devices holding local data samples, without exchanging them.
Funded by EISMEA
This project is funded by the European Innovation Council and SMEs Executive Agency (EISMEA) under the EIC Accelerator program. It’s a two-year initiative that commenced on May 1, 2023, and is backed by a grant of €2,499,874.
Innovations
Enhanced data privacy and security while harnessing rich, localised data directly where it is generated, optimising both computational efficiency and real-time decision making capabilities
Synthesis Key Innovations
Streamlined Model Management
Simplifies the process of creating, deploying, and managing machine learning models, leading to optimized resource utilization and scalable models.​
Intelligent Clustering & Federated Learning
Provides automated clustering of models for efficient federated learning, based on performance metrics and other defining characteristics.​
Automated Anomaly Detection
Leverages advanced algorithms to autonomously spot system anomalies and outliers, reducing manual oversight and bolstering system reliability.
Holistic Lifecycle Management
Offers an end-to-end solution for the entire machine learning model lifecycle, from creation to deployment and ongoing monitoring.
User-Friendly Interfaces & Connectivity
Features intuitive dashboards and APIs for real-time monitoring, decision-making, and seamless integration with existing infrastructures.
Federated Learning: Why It Matters
Federated Learning is a revolutionary approach in machine learning where a model is trained across multiple decentralized edge devices holding local data samples, without exchanging them. This paradigm enhances data privacy and security, while still allowing for the collaborative power of global model improvements. As edge devices continue to proliferate, the relevance of federated learning will only grow. It offers the ability to harness rich, localized data directly where it is generated, optimizing both computational efficiency and real-time decision-making capabilities
European Innovation Council
The European Innovation Council (EIC) was established by the European Commission in 2021 following a 3 years successful pilot phase. It has a mission to identify, develop and scale up breakthrough technologies and disruptive innovation. It has a budget of over €10 billion for the period 2021-2027.
​
The funding and support is organised into three main funding schemes covering all technology readiness levels: EIC Pathfinder for advanced research to develop the scientific basis to underpin breakthrough technologies; EIC Transition to validate technologies and develop business plans for specific applications; and the EIC Accelerator to support companies (SMEs, start-ups, spin-outs and in exceptional cases small mid-caps) to bring their innovations to market and scale up. The Accelerator provides a combination of grant support and direct equity investments in companies through a dedicated EIC Fund, which also provides a platform for co-investments with other investors.
​
For all schemes, the direct financial support is augmented with access to a range of Business Acceleration Services.
The strategy and implementation of the EIC is overseen by the EIC Board of twenty individuals from the innovation ecosystem (academia, business, investment, ecosystem builders). The EIC also employs dedicated Programme Managers with high level expertise in their fields, to set the challenges and proactively manage portfolios of projects towards technological breakthroughs.