A hyperparameter is a configuration value set before or during the training of a machine learning model that controls how the learning process operates. Unlike model parameters, which are learned automatically from training data, hyperparameters are selected by the developer or optimized through systematic methods. Examples include learning rate, batch size, number of training epochs, tree depth, and the number of layers in a neural network.
Hyperparameters are commonly used in machine learning, deep learning, computer vision, natural language processing, and predictive analytics. Their purpose is to influence how effectively a model learns and generalizes to new data. Choosing suitable values can improve accuracy, training speed, stability, and overall performance. Techniques such as grid search, random search, and Bayesian optimization are often used to identify effective hyperparameter combinations for a particular dataset and model.
