Print Email Facebook Twitter Model-specific Explainable Artificial Intelligence techniques: State-of-the-art, Advantages and Limitations Title Model-specific Explainable Artificial Intelligence techniques: State-of-the-art, Advantages and Limitations Author Khan, Arghem (TU Delft Electrical Engineering, Mathematics and Computer Science) Contributor Lal, C. (mentor) Conti, M. (mentor) Degree granting institution Delft University of Technology Programme Computer Science and Engineering Project CSE3000 Research Project Date 2022-06-30 Abstract Artificial Intelligence (AI) and Machine learning (ML) applications are being widely used to solve different problems in different sectors. These applications have enabled the human-effort and involvement to be very low. The AI/ML systemsmake their own predictions and do not require a great deal of human help. However, over the last few years several incidents of the developed systemshave led to questions regarding the transparency of those AI/ML systems. Without expertise, it is not always as straightforward to understandcertain predictions. This pressing issue has led to the emerging topic of Explainable Artificial Intelligence (XAI). In this research, we will present the current work on a specific type of XAI, namely model-specific XAI. Model-specific XAI techniques are particular to certain types of ML techniques. We will look into several recent model-specific XAI techniques and provide the advantagesand disadvantages. Within similarities we find that there is a set of general requirements that the techniques should adhere to (expertise, bias, time, privacyand performance). We characterize the techniques in feature-based, concept-based and logic-based. With regard to future work, there is room forimprovement on several areas. For example, this includes work from exploring hybrid techniques to investigating how current techniques can improvethe privacy. Subject Artificial IntelligenceMachine LearningExplainable Artificial IntelligenceModel-SpecificDeep Learning To reference this document use: http://resolver.tudelft.nl/uuid:b8ca8774-47f3-40c1-bc7a-97bce1e176a1 Part of collection Student theses Document type bachelor thesis Rights © 2022 Arghem Khan Files PDF Research_Paper_Arghem_Kha ... _final.pdf 901.6 KB Close viewer /islandora/object/uuid:b8ca8774-47f3-40c1-bc7a-97bce1e176a1/datastream/OBJ/view