Fuzzy Cognitive Maps: Their Role in Explainable Artificial Intelligence

Currently, artificial intelligence is facing several problems with its practical implementation in various application domains. The explainability of advanced algorithms a topic paramount importance, and many discussions have been held recently. Pioneering classical machine learning deep models behave as black boxes, constraining the logical interpretations that end users desire. Artificial applications industry, medicine, agriculture, social sciences require users’ trust systems. Users are always entitled to know why how each method has made decision which factors play critical role. Otherwise, they will be wary using new techniques. This paper discusses nature fuzzy cognitive maps (FCMs), soft computational model human knowledge provide decisions handling uncertainty. Though FCMs not field, evolving incorporate recent advancements intelligence, such convolutional neural networks. reveals their supremacy transparency, interpretability, transferability, other aspects explainable (XAI) methods. present study aims reveal defend properties highlight successful Subsequently, cope XAI directions presents examples from literature demonstrate superiority. results both accordance directives domains medical decision-support systems, precision energy savings, environmental monitoring, policy-making for public sector.