# What is Hyperparameter? Definition & Technical Mechanics

> **Source:** [SPIDITS AI AI Glossary](https://spidits.com/ai-glossary)  
> **Category:** Model Training  
> **Canonical Citation:** [https://spidits.com/ai-glossary/hyperparameter](https://spidits.com/ai-glossary/hyperparameter)

## Definition
A Hyperparameter is a configuration variable whose value is set before the machine learning training process begins. Unlike standard parameters (weights and biases) which are learned automatically during training, hyperparameters control the learning behavior itself.

## Architectural Mechanics & Deep Dive
A hyperparameter is a configuration variable whose value is set before the training process begins, rather than being learned by the model during training. Examples include learning rate, batch size, number of hidden layers, and dropout rate. Finding the optimal configuration of hyperparameters is a critical step in training machine learning models, often performed using search strategies like grid search, random search, or Bayesian optimization.

## Industry Applications & Real-World Use Cases
Model optimization, tuning runs, and training configuration

## Frequently Asked Questions

### What are some common hyperparameters?
Learning rate, batch size, number of epochs, activation function type, and dropout rate.

### What is hyperparameter tuning?
The process of searching for the optimal combination of hyperparameters (using grid search, random search, or Bayesian optimization) to maximize model accuracy.

## Related Terminology
- [backpropagation](https://spidits.com/ai-glossary/backpropagation)
- [epoch](https://spidits.com/ai-glossary/epoch)

---
*From the SPIDITS AI Knowledge Base (300+ terms indexed). Explore full technical definitions: [https://spidits.com/ai-glossary](https://spidits.com/ai-glossary)*