Explaining deep neural networks by leveraging intrinsic methods

Deep neural networks have been pivotal in driving AI advancements over the past decade, revolutionizing domains such as gaming, biology, autonomous systems, and voice and text assistants. Despite their impact, these networks are often regarded as black-box models due to their intricate structures and the absence of explanations for their decisions. This opacity poses a significant challenge to AI systems' wider adoption and trustworthiness. This thesis addresses this issue by contributing to the field of eXplainable AI, focusing on enhancing the interpretability of deep neural networks. The core contributions lie in introducing novel techniques aimed at making these networks more interpretable by leveraging an analysis of their inner workings. Specifically, the contributions are threefold. Firstly, the thesis introduces designs for self-explanatory deep neural networks, such as the integration of external memory for interpretability purposes and the usage of prototype and constraint-based layers across several domains. These proposed architectures are specifically designed to preserve most of the black-box networks, thereby maintaining or improving their performance. Secondly, this research delves into novel investigations on neurons within trained deep neural networks, shedding light on overlooked phenomena related to their activation values. Lastly, the thesis conducts an analysis of the application of explanatory techniques in the field of visual analytics, exploring the maturity of their adoption and the potential of these systems to convey explanations to users effectively. In summary, this thesis contributes to the growing field of Explainable AI by proposing intrinsic techniques to enhance the interpretability of deep neural networks. By mitigating the opacity issue of deep neural networks and applying them to several different applications, the research aims to foster trust in AI systems and facilitate their wider adoption across several applications.