References and further reading

1. In this book, we use the terms interpretable and explainable AI interchangeably, but it is important to note that there are differences in opinion among the researchers about their definitions. Typically, explainable AI is focused on providing insights into how the AI system arrived at a particular decision, while interpretability is the discipline of making the AI system itself more understandable by making the individual components transparent. Transparency refers to systems where the inner workings are completely open and accessible, while explainable AI may only require that some level of understanding be possible. Generally speaking, explainable AI is more concerned with human-centered concerns such as usability and trustworthiness, while interpretable AI focuses more on providing information that can be used to improve the model or debug errors. However, both approaches are necessary for creating safe and effective AI systems.
2. https://arxiv...