In machine learning, hyperparameters are parameters that are set prior to training a model and control the learning process. Unlike model parameters, which are learned during training, hyperparameters are not directly learned from the data but are instead specified by the user or determined through a trial-and-error process. Hyperparameters govern aspects of the learning algorithm's behavior, such as the complexity of the model, the learning rate, the regularization strength, the number of layers or nodes in a neural network, and the choice of optimization algorithm. Tuning hyperparameters is essential for optimizing model performance and generalization to unseen data. Techniques such as grid search, random search, and Bayesian optimization are commonly used to search for the optimal hyperparameters for a given machine learning task.

Note: This concise definition provides an overview of Hyperparameter. For further information, a more in-depth search on Google is recommended.