Interpretability
The degree to which a human can understand the internal mechanisms and reasoning process of a machine learning model. More interpretable models allow deeper inspection of how they work.
Why It Matters
Interpretability builds trust and enables debugging. When a model makes a mistake, interpretability tells you why, so you can fix it.
Example
A decision tree model where you can trace the exact path of decisions that led to a specific prediction, versus a deep neural network where the reasoning is opaque.
Think of it like...
Like the difference between a glass-walled kitchen where you see everything being prepared versus a closed kitchen — both produce food, but one lets you understand how.
Related Terms
Explainability
The ability to understand and articulate how an AI model reaches its decisions or predictions. Explainable AI (XAI) makes the decision-making process transparent and comprehensible to humans.
Transparency
The principle that AI systems should operate in a way that allows stakeholders to understand how they work, what data they use, and how decisions are made.
Black Box
A model or system whose internal workings are not visible or understandable to the user — you can see the inputs and outputs but not the reasoning in between. Most deep learning models are considered black boxes.