A Survey on Methods for Explainability in Deep Learning Models

In recent years, there has been a significant increase in the use of deep learning (DL) models in various fields, including image recognition, natural language processing, autonomous vehicles, and healthcare. While these models have demonstrated remarkable performance, they often operate as black boxes and lack transparency and interpretability in their decision-making processes. This challenge has led to the emergence of Explainable Artificial Intelligence (XAI), which aims to elucidate the inner workings of DL models and provide insight into their predictions. This survey provides a comprehensive overview of state-of-the-art methods for enhancing the explainability of DL models. We explored a diverse range of techniques and methods in XAI, as well as the DL models, libraries, tools, and frameworks used in the XAI domain. In addition, we discuss future research directions in this field. This survey aims to guide researchers, practitioners, and policymakers in navigating the complex landscape of explainability in DL models and in fostering trust and transparency in AI systems.