# Training (AI)

> The learning stage of AI. A model practises on examples until its guesses get good.

**Field:** Artificial Intelligence  
**Category:** Foundations  
**Also known as:** Model Training, AI Training

## Think of it like

Think of it like piano practice. Each mistake makes the next try a bit better.

## Definition

Training is how an AI model learns. The model sees many examples and makes a guess for each one. Its guess is checked against the right answer. Then its numbers are nudged so the next guess is a little closer. This repeats millions of times until the guesses are good. Big models can take weeks to train on many powerful chips.

## Example

Jack trains a model on 10,000 photos of cats and dogs, each labelled. After training, it can sort new photos it has never seen.

## Why it matters

Training is the slow and costly part. Once it is done, the model can be used again and again for little cost.

## Common mistake

Thinking a chatbot keeps training while you talk to it. Most models stopped learning before you ever met them.

## Three principles

- **Guess and check.** Each guess is compared with the answer.
- **Small nudges.** The numbers change a little each time.
- **Done before use.** Training ends, then the model ships.

## Related terms

- [Inference (AI)](https://learn.benibix.com/term/ai/inference)
- [AI Model](https://learn.benibix.com/term/ai/ai-model)
- [Machine Learning](https://learn.benibix.com/term/ai/machine-learning)
- [Training Data](https://learn.benibix.com/term/ai/training-data)
- [AI Compute](https://learn.benibix.com/term/ai/ai-compute)

## Told apart from

- [Training vs Inference](https://learn.benibix.com/compare/training-vs-inference): People often think a chatbot learns from them while they talk. It does not. Training is when a model learns, and it is over before the model is shared. Inference is each time the model answers you. The model stays the same then, so your chat does not teach it.

## Taught in

- [AI Training and Inference](https://learn.benibix.com/learn/ai-foundations/ai-training-and-inference): AI Basics, 2/10

![Top row, training: many labelled examples flow into a model whose numbers get nudged. Bottom row, inference: one new photo goes into the finished model and the answer cat comes out.](https://learn.benibix.com/diagrams/ai-training-inference.svg)

---

Source: https://learn.benibix.com/term/ai/training
Author: Behnia Zarei (a developer in Vienna, Austria, who builds and teaches data, AI and business intelligence at BENIBIX)
Publisher: BENIBIX Learn (https://learn.benibix.com/)
Last updated: 2026-11-17
Licence: CC BY 4.0 (https://creativecommons.org/licenses/by/4.0/). Quote freely with attribution.
