AI engineering glossary · ML fundamentals
What is inference?
Inference (also called Prediction, Scoring): Using an already trained model to produce predictions for new inputs. It does not change the model's parameters. Speed, cost and reliability at this stage matter greatly in real products.
Inference: an example
Sending a new customer's details to the trained churn model and receiving a 0.31 churn probability is inference.
Related terms
- Training
- Model
- Batch learning
- Online learning
More ML fundamentals terms
- Inter-annotator agreement
- Irreducible error
- k-fold cross-validation
- L1 regularisation
- L2 regularisation
- Label
- Label noise
- Latent variable
Where you learn it
Inference is part of the AI Engineering Program, which teaches it with notes, a hands-on lab and an exam. The first lesson is free.