Comprehensibility

Explainability means that when you need to understand or solve a problem, you can get the relevant information you need.

Interpretability at the data level: Let the neural network have a clear symbolic expression of internal knowledge to match the human knowledge framework, so that people can diagnose and modify the neural network at the semantic level.

Interpretability of machine learning: The decision tree model can be regarded as an interpretable model, which plays a key role in related research. Deep neural networks are often regarded as black box models. Interpretability is the feature that makes the model interpretable.