Special Session

Explainable Artificial Intelligence for Industry 4.0

This special session deals with the problem of extracting valuable knowledge from the given data, a problem that is especially felt by data scientists involved in IoT and Big Data projects. The focus of the SS is on knowledge representation and enhancement of human-machine interaction. As remarked by DARPA, "even though current AI systems offer many benefits in many applications, their effectiveness is limited by a lack of explanation ability when interacting with humans". Accordingly, users require a new generation of explainable AI systems that are expected to naturally interact with them, by providing comprehensible explanations of decisions automatically made. This is also aligned with the European vision for AI (CLAIRE) which remarks the need of building trustworthy AI that is beneficial to people through fairness, transparency and explainability.

The goal is to discuss and disseminate the most recent advancements focused on explainable AI in the scenario of Industry 4.0. This is strongly characterized by tight collaborations of humans and smart factories in highly complex processes, thus requiring mutual intelligibility and exchange of meaningful information and knowledge. The session goes a step ahead with respect to the previous events we organized, including the latest NLG 2018, IPMU 2018 and FUZZ’IEEE 2019.

Scope and topics

Explainable Computational Intelligence
Theoretical Aspects of Interpretability
Dimensions of Interpretability: Readability versus Understandability
Learning Methods for Interpretable Systems and Models
Interpretability Evaluation and Improvements
Models for Explainable Recommendations
Design Issues
Successful Applications of Interpretable AI Systems

Interpretable Machine Learning
Interpretable Fuzzy Systems
Relations between Interpretability and other Criteria (such as Accuracy, Stability, Relevance, etc.)
Explainable Agents
Self-explanatory Decision-Support Systems
Argumentation Theory for Explainable AI
Natural Language Generation for Explainable AI
Interpretable Human-Machine Interaction

Notes

Papers must be submitted electronically for peer review through PaperCept by ~~March 31~~ April 14, 2019. In PaperCept, click on the SMC 2019 link “Submit a Contribution to SMC'19” and follow the steps. Session area is: Cybernetics.

All papers must be written in English and should describe original work. For guidelines, please follow the SMC website link.