Descripción del proyecto
Mejora de la IA para predecir eventos complejos
Numerosas aplicaciones dependen de la inteligencia artificial (IA) para afrontar los flujos de información, en constante evolución. El proyecto EVENFLOW, financiado con fondos europeos, desarrollará técnicas de aprendizaje híbrido para predecir eventos cambiantes complejos. Utilizará tanto técnicas de aprendizaje por representación neuronal, capaces de obtener características basadas en eventos a partir de corrientes de datos perceptivos, como herramientas de razonamiento y aprendizaje simbólico. Los métodos de aprendizaje estarán en línea, por lo que podrán aprovechar los abundantes datos especializados que van estando disponibles a lo largo del tiempo. EVENFLOW se pondrá a prueba con tres casos: el pronóstico oncológico en la medicina de precisión, el comportamiento seguro y eficiente de los robots de transporte autónomos en fábricas inteligentes y la evaluación fiable del ciclo de vida para infraestructuras críticas.
Objetivo
A growing number of applications rely on AI-based solutions to carry-out mission-critical tasks, many of which are of temporal nature, dealing with ever-evolving flows of information. Crucial for mitigating threats and taking advantage of opportunities in such domains, is the ability to forecast imminent situations and critical complex events ahead of time. EVENFLOW will 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 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 utilize such features to synthesize 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 utilize rich domain knowledge that is becoming available progressively, over time. To deal with the brittleness of neural predictors and the high volume/velocity of temporal data flows, the EVENFLOW techniques will rely on novel, formal verification techniques for machine learning, in addition to a suite of scalability algorithms for federated training and incremental model construction. The learnt forecasters will be interpretable and scalable, allowing for fully explainable insights, delivered in a timely fashion and enabling proactive decision making. EVENFLOW will be evaluated on three challenging use cases related to oncological forecasting in precision medicine, safe and efficient behavior of autonomous transportation robots in smart factories and reliable life cycle assessment of critical infrastructure.
Ámbito científico
Palabras clave
Programa(s)
Régimen de financiación
HORIZON-RIA - HORIZON Research and Innovation ActionsCoordinador
1050 Bruxelles / Brussel
Bélgica