AI Glossary
Inference
Applying a trained model to new data to generate predictions.
Definition
Inference refers to the application of a trained AI model to new, unseen data to generate a prediction or output. It is the counterpart to training: during training the model learns, during inference it applies what it has learned. Every ChatGPT response is an inference – the model calculates the most likely continuation of the text.
Related Terms
Sources: a16z AI Glossary