A black-box machine learning algorithm is one were the internal details are eiether not available or too complex to comorehend. A deep neural network is a good example. With potentially billions of weights and nodes, it is not easy to understand what is going on inside. In some cases it may be acceptable to simply accept the black-box model as an oracle, gining answers that are trusted, even oif not understood. However, in other cases the decisoons being made may be safety-critical or there may be issues of legal responsibility; in such cases, explainable AI is essential.
Used on page 522