OLUD

2nd Edition of Explainable Online Learning from Uncertain Data Streams:

Special Session at the EAIS 2024

23-24 May 2024, Madrid, Spain

within the IEEE EAIS 2024 -

IEEE International Conference on Evolving and Adaptive Intelligent Systems

Nowadays, applications and systems in various domains (computer science, engineering, medicine, meteorology, economy, etc.) are based on real-world measures and depend on data transmission and data pre-processing. Effective modeling approaches to address such a large amount of dynamically-changing data in a feasible timeframe are of utmost importance. Traditional modeling approaches for static datasets are very often insufficient or ineffective for online data streams due to the fact that fast recursive procedures are required to attend to narrow time and memory constraints. Models must be updated (parametrically and structurally) to unknown changes of the data sources. Moreover, data streams may carry statistical, possibilistic and fuzzy uncertainties that arise in specific technical and contextual domains, which need to be adequately addressed. Finally, explainable models are needed in several domains in which the final users are non-technicians. Thus, new methods to linguistically explain the reasoning behind the outcomes of a model are needed in order to trust and understand predictions. The special session Explainable Online Learning from Uncertain Data Streams (OLUD) at the IEEE EAIS 2024 addresses uncertainty, explainability and online machine learning using deep neural networks, fuzzy rule-based systems, granular computing systems, decision trees, support vector machines, ensembles, and so on, leaving room to several open questions: 

(i) how explainability can be achieved and monitored in online learning? 

(ii) how uncertainty can improve online learning? 

(iii) how hybrid methods could be combined to exploit their benefits for online learning? 

Acknowledgements