Explainable Artificial Intelligence: a Systematic Review

TL;DR

This systematic review analyzes the rapid growth of XAI methods, categorizing them into four clusters, summarizing current advancements, and suggesting future research directions to improve explainability in AI models.

Contribution

It provides a hierarchical classification of XAI methods, consolidates current knowledge, and offers a structured overview of the field for future research guidance.

Findings

Hierarchical classification of XAI methods

Summary of state-of-the-art in XAI

Recommendations for future research directions

Abstract

Explainable Artificial Intelligence (XAI) has experienced a significant growth over the last few years. This is due to the widespread application of machine learning, particularly deep learning, that has led to the development of highly accurate models but lack explainability and interpretability. A plethora of methods to tackle this problem have been proposed, developed and tested. This systematic review contributes to the body of knowledge by clustering these methods with a hierarchical classification system with four main clusters: review articles, theories and notions, methods and their evaluation. It also summarises the state-of-the-art in XAI and recommends future research directions.