Inference vs Model training

Why they differ

Training is the slow, one-off stage where the model learns; inference is every later use, where it only applies what it learned.

Inference

Machine learning basics

Using an already trained model to produce an answer for new input, which is what happens each time you ask a chat assistant something.

Formal

The stage where a trained model, with its weights fixed, is run on new input to produce an output such as a label, a score or generated text; the model does not learn from the input by doing so.

In plain English

Like a trained doctor looking at a new patient; the years of study are over, and now the knowledge is simply being used.

In practice

When a clerk in a municipality pastes a contract into an online AI tool and asks for a summary, the text is sent to the provider's servers abroad, where inference runs.

Why it matters

Where inference runs decides where your data travels and who can see it; a local model and a foreign cloud service carry very different risks.

Model training

Machine learning basics

The costly, one-off stage where a model looks at training data again and again and tunes its internal numbers until its guesses improve.

Formal

The process of repeatedly feeding training data to a model, measuring how far its outputs are from the wanted answers, and adjusting its weights to shrink that gap; the result is a fixed set of learned numbers.

In plain English

Like a darts player throwing thousands of darts, checking how far each lands from the centre, and adjusting their arm a little each time.

In practice

A Danish university books weeks of time at a national computing centre to train a Danish language model once; municipalities and firms that adopt it then only use the finished result.

Why it matters

What happens here decides what the model knows and how it behaves; it is also where poisoned or unlawful data gets built in for good.

Shared connections

Graphics processing unit (GPU)Machine learning