Inference
The act of running a trained model to get an answer. In law the word means something else: a conclusion drawn from evidence.
The fuller definition
In machine learning, inference means running a trained model on input to produce a prediction or generated output.
- Loaded model
Existing weights
- New input
Current task
- Result
Prediction or generated text
A simplified relationship, not a screenshot or a complete design.
A concrete example
Each response from a loaded local language model involves inference on your input and the growing output.
The distinction that matters
This technical meaning differs from a lawyer's inference from evidence. Ordinary inference does not necessarily update model weights.
Related terms
Training
Adjusting a model with examples and a learning rule. The aim is to improve how it handles tasks.
Hardware & hostingLocal model
A model that runs on your own computer, so your documents never leave it.
APIs & softwareLatency
The wait between sending a request and getting the answer back.
Where it is taught
What actually happens when you ask AI a question?Source and further reading
Google · Machine Learning GlossaryThe definition and example are written for this library. The link gives background, official documentation or legal authority as labelled. Legal scope depends on the jurisdiction and current text; product features depend on release and settings.