The implementation of Artificial Intelligence (AI) has boosted production efficiency, workplace safety and customer satisfaction by automating processes.
But despite the high accuracy of powerful tools such as deep learning and reinforcement learning techniques, AI is considered unintelligible to humans. The “black box” approach used in AI negatively affects users’ trust in the system, a critical factor in the context of decision making. The solution to this opacity is Explainable Artificial Intelligence (XAI) which pursues model transparency.
This open dialogue will focus on the integration of explainability as a concept but also as a main design element in industrial AI processes while takeing into account different approaches from other EU projects such as COALA and STAR.
