AI engineering glossary · AI ethics law product
What is black-box model?
Black-box model (also called opaque model): A model whose internal workings are too complex or hidden for people to follow, so we can see inputs and outputs but not why a given output was produced. Deep neural networks and large ensembles are typical examples, and they often need separate explanation tools.
Black-box model: an example
A gradient-boosted ensemble of 500 trees predicts default risk accurately, but no one can read its reasoning directly.
Related terms
- Interpretability
- Post-hoc explanation
- Surrogate model
- Explainable AI
More AI ethics law product terms
- Conformity assessment
- Consent
- Consent Manager
- Contestability
- Copyright and AI training data
- Cost per resolved query
- Counterfactual explanation
- Counterfactual fairness
Where you learn it
Black-box model is part of the AI Engineering Program, which teaches it with notes, a hands-on lab and an exam. The first lesson is free.