The European project EVENFLOW which stands for Robust Learning and Reasoning for Complex Event Forecasting kicked-off on 13 and 14 of October in Athens on the premises of coordinator Netcompany-Intrasoft. During the two-day meeting, the European Commission Project Officer, Mr. Miguel Angel Rubio Escudero welcomed the partners, while representatives of all six partners, presented their role in the project.
EVENFLOW is funded under the Horizon Europe funding framework on the Artificial Intelligence & Robotics domains, and is a three year project which aims to develop hybrid learning techniques for complex event forecasting, which combine deep learning with logic-based learning and reasoning into neuro-symbolic forecasting models.
The envisioned methods to employed will combine (i) neural representation learning techniques, capable of constructing event-based features from streams of perception-level data with (ii) powerful symbolic learning and reasoning tools, that utilise such features to synthesise high-level, interpretable patterns of critical situations to be forecast. Crucial in the EVENFLOW approach is the online nature of the learning methods, which makes them applicable to evolving data flows and allows to utilise rich domain knowledge that is becoming available progressively, over time.
EVENFLOW will be evaluated on three challenging use cases related to oncological forecasting in precision medicine, safe and efficient behaviour of autonomous transportation robots in smart factories and reliable life cycle assessment of critical infrastructure.
The partnership consists of six partners from five countries: coordinator Netcompany-Intrasoft (Belgium), the National Centre for Scientific Research Demokritos (Greece), the ATHENA Research Innovation Information Technologies (Greece), the Barcelona Supercomputing Center (Spain), the German Research Centre for Artificial Intelligence (Germany) and Ekso (Italy).