A Survey on Understanding, Visualizations, and Explanation of Deep Neural Networks

TL;DR

This survey reviews recent methods for understanding, visualizing, and explaining deep neural networks to improve transparency and trust in critical applications, highlighting the current state and challenges in explainable AI.

Contribution

It provides a comprehensive overview of techniques for interpreting and visualizing DNNs, emphasizing the importance of explainability in sensitive domains.

Findings

Deep learning models are often black boxes, hindering trust.

Recent efforts have advanced explainability methods for DNNs.

Explainable AI is still an emerging field with ongoing challenges.

Abstract

Recent advancements in machine learning and signal processing domains have resulted in an extensive surge of interest in Deep Neural Networks (DNNs) due to their unprecedented performance and high accuracy for different and challenging problems of significant engineering importance. However, when such deep learning architectures are utilized for making critical decisions such as the ones that involve human lives (e.g., in control systems and medical applications), it is of paramount importance to understand, trust, and in one word "explain" the argument behind deep models' decisions. In many applications, artificial neural networks (including DNNs) are considered as black-box systems, which do not provide sufficient clue on their internal processing actions. Although some recent efforts have been initiated to explain the behaviors and decisions of deep networks, explainable artificial intelligence (XAI) domain, which aims at reasoning about the behavior and decisions of DNNs, is still in its infancy. The aim of this paper is to provide a comprehensive overview on Understanding, Visualization, and Explanation of the internal and overall behavior of DNNs.