This track focuses on the integration of explainable AI techniques in predictive maintenance applications within engineering contexts. Participants will explore methodologies that enhance model interpretability and transparency in maintenance decision-making processes.

This session will delve into the development and application of interpretable models in supervised learning frameworks. Researchers will present novel approaches that balance model accuracy with the need for transparency and understanding.

This track addresses the challenges and innovations in unsupervised learning techniques for anomaly detection in engineering systems. Discussions will center on the interpretability of models and their practical implications in real-world scenarios.

This session will explore various methods for assessing feature importance in machine learning models. Participants will discuss the implications of these techniques on model evaluation and their role in enhancing explainability.

This track focuses on the latest frameworks and methodologies developed to enhance the interpretability of deep learning models. Researchers will share insights on bridging the gap between complex model architectures and human comprehension.

This session will investigate the role of human-in-the-loop approaches in the development of explainable AI systems. Emphasis will be placed on how human feedback can improve model transparency and trustworthiness.