Home › Glossary › Training
Core · beginner

What is Training?

A plain-English explanation of Training (Model Training) — what it means, why it matters, and how it is used in AI.

Training
Model Training
Training is the process by which an AI model learns patterns from data by repeatedly adjusting its internal parameters (weights) to minimise errors in its predictions.
"Training GPT-4 involved processing trillions of tokens of text across thousands of GPUs over several months."

Also known as: Model training, pre-training, learning

Fine-tuningDatasetWeightsGPU

Why does Training matter?

Training determines what a model knows and how it behaves. Fine-tuning is a cheaper form of additional training on specialised data.

Practice this term

The best way to remember Training is to practice unscrambling it. AI Terminology Scrambler uses spaced repetition to help you learn and retain AI vocabulary in just a few minutes a day.

Practice Training now →

Related AI terms

Fine-tuningDatasetWeightsGPU