SIDU: Similarity Difference and Uniqueness Method for Explainable AI

Although there have been a number of early studies focusing on generating explanation schemes for deep network A new brand of technical artificial intelligence (Explainable models, considering the complexity of such a challenging task AI) research has focused on trying to open up the'black box' there is still much more effort needed to establish both reliable and provide some explainability. This paper presents a novel quantitative and qualitative methods in this new field. The visual explanation method for deep leaning networks in the majority of the proposed methods are based on generating visual form of a saliency map that can effectively localize entire object feature explanations known as saliency maps.