# Hyperparameter

> A setting you pick before training. It shapes how the model learns.

**Field:** Artificial Intelligence  
**Category:** Machine Learning  
**Also known as:** Hyper-parameter, Training Setting

## Think of it like

Think of it like the oven heat you pick before you bake. The cake does not choose it.

## Definition

A hyperparameter is a setting you choose before training starts. It shapes how the model learns, but the model does not learn it. Examples are how big each learning step is, how deep a tree may grow, or how many layers a network has. People try a few values and keep the one that works best. That search is called tuning.

## Example

Lucy trains the same model three times, with steps of size 0.1, 0.01 and 0.001. The middle one gives the best results, so she keeps it.

## Why it matters

The same data and method can give a good or a bad model, just from these settings. Tuning them is a normal part of the job.

## Common mistake

Tuning the settings by checking the test set. Use the validation set for that. If not, your final score will look too good.

## Three principles

- **Chosen by you.** Set before training starts.
- **Shapes learning.** Not learned by the model.
- **Found by trying.** Test a few and keep the best.

## Related terms

- [Model Parameter](https://learn.benibix.com/term/ai/model-parameter)
- [Validation Set](https://learn.benibix.com/term/ai/validation-set)
- [Training (AI)](https://learn.benibix.com/term/ai/training)
- [Machine Learning](https://learn.benibix.com/term/ai/machine-learning)
- [Experiment Tracking](https://learn.benibix.com/term/ai/experiment-tracking)
- [Hyperparameter Tuning](https://learn.benibix.com/term/ai/hyperparameter-tuning)

## Told apart from

- [Model Parameter vs Hyperparameter](https://learn.benibix.com/compare/model-parameter-vs-hyperparameter): People often think both are learned in training. Only one is. Parameters are the numbers inside the model, and training finds them. Hyperparameters are the settings you pick first, like the size of each step. You set those by hand. The rest you never touch.

## Taught in

- [Hyperparameter Tuning](https://learn.benibix.com/learn/ai-machine-learning/hyperparameter-tuning): Machine Learning, 12/18

![A box marked model holds a grid of numbers labelled learned in training. Outside the box, three dials marked learning rate, tree depth and number of layers are labelled set by you before training.](https://learn.benibix.com/diagrams/ml-parameters.svg)

---

Source: https://learn.benibix.com/term/ai/hyperparameter
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.
