In recent years, the intersection of tree-based methods and advanced activation functions
has led to remarkable advancements in deep learning. This paper presents novel …

2 Background & Related Work 16 2.1 Motivation For Explainable AI.................... 16 2.2 XAI
For DL Through Feature Importance............. 18 2.3 Population Feature Selection …

Interpretability in deep learning is one of the largest obstacles to more widespread adoption
of deep learning in critical applications. A variety of methods have been introduced to …

Deep learning techniques have been actively researched for solving complex and diverse
problems, demonstrating high performance across various AI domains. However, the …

Interpretability in deep learning is one of the largest obstacles to its more widespread
adoption in critical applications. A variety of methods have been introduced to understand …

With the advent of highly predictive but opaque deep learning models, it has become more
important than ever to understand and explain the predictions of such models. Existing …

A good AI algorithm can make accurate predictions and provide reasonable explanations for
the field in which it is applied. However, the application of deep models makes the black box …

While neural networks can provide high predictive performance, it was a challenge to
identify the salient features and important feature interactions used for their predictions. This …

Deep learning has revolutionized various fields by enabling the development of complex
models capable of learning from vast amounts of data. However, the inner workings of deep …

Feature importance ranking has become a powerful tool for explainable AI. However, its
nature of combinatorial optimization poses a great challenge for deep learning. In this paper …