Explaining Explanations: An Overview of Interpretability of Machine Learning

TL;DR

This paper reviews the current state of explainability in machine learning, emphasizing the importance, challenges, and future directions for creating transparent and fair AI systems.

Contribution

It provides a comprehensive overview of interpretability methods, classifies existing approaches, and highlights open challenges and future research directions in XAI.

Findings

Current explanations lack standardization and systematic assessment.

Deep neural network explanations are often insufficient.

Future research should focus on developing standardized and effective interpretability methods.

Abstract

There has recently been a surge of work in explanatory artificial intelligence (XAI). This research area tackles the important problem that complex machines and algorithms often cannot provide insights into their behavior and thought processes. XAI allows users and parts of the internal system to be more transparent, providing explanations of their decisions in some level of detail. These explanations are important to ensure algorithmic fairness, identify potential bias/problems in the training data, and to ensure that the algorithms perform as expected. However, explanations produced by these systems is neither standardized nor systematically assessed. In an effort to create best practices and identify open challenges, we provide our definition of explainability and show how it can be used to classify existing literature. We discuss why current approaches to explanatory methods especially for deep neural networks are insufficient. Finally, based on our survey, we conclude with suggested future research directions for explanatory artificial intelligence.