Towards Explainable Artificial Intelligence
It tackles the issue of explainability in AI for domains requiring transparency, such as healthcare, but is incremental as it primarily surveys existing work.
This paper addresses the problem of deep learning models being 'black boxes' that lack transparency, particularly in critical applications like medicine, by reviewing recent developments in methods for visualizing, explaining, and interpreting these models to advocate for their wider practical use.
In recent years, machine learning (ML) has become a key enabling technology for the sciences and industry. Especially through improvements in methodology, the availability of large databases and increased computational power, today's ML algorithms are able to achieve excellent performance (at times even exceeding the human level) on an increasing number of complex tasks. Deep learning models are at the forefront of this development. However, due to their nested non-linear structure, these powerful models have been generally considered "black boxes", not providing any information about what exactly makes them arrive at their predictions. Since in many applications, e.g., in the medical domain, such lack of transparency may be not acceptable, the development of methods for visualizing, explaining and interpreting deep learning models has recently attracted increasing attention. This introductory paper presents recent developments and applications in this field and makes a plea for a wider use of explainable learning algorithms in practice.