Inference
In AI, inference is the stage where a trained model is used to produce outputs, such as predictions or generated text, from new inputs.
What is Inference?
Training builds the model; inference is the model at work answering queries. For widely used generative AI services, the total computing cost of inference can exceed that of training. The EU AI Act treats the capability to infer how to generate outputs as a defining feature of an AI system.
How it works
Input data is converted into the model's format, passed through the model's computations using its fixed learned parameters, and the output is returned to the user or application.
← All Artificial Intelligence & Superintelligence definitions · ← Back to the A–Z definitions