← Concept IndexDEFINITION WHY IT MATTERS COMMONLY CONFUSED WITH
What a model actually is
Also called: neural network, weights, parameters
A model is a large set of numbers (parameters) tuned during training so that, given some input, it predicts a useful output. It is not a database of answers and it does not look things up.
If you think of a model as a search engine, its confident wrong answers are baffling. If you think of it as a pattern-predictor, they make sense — and you start checking the things that matter.
A search index or knowledge base. A model has no stored 'records' to retrieve; it reconstructs plausible text from patterns.