Tuning, also known as model tuning or fine-tuning, is a critical process in artificial intelligence (AI) and machine learning that involves optimizing the performance of a trained model by adjusting its hyperparameters or architecture. Hyperparameters are configuration settings that are not learned during the training process but significantly influence how a model learns and generalizes from the data. Tuning aims to fine-tune these hyperparameters to achieve the best possible model performance on new, unseen data.
The tuning process typically involves iteratively adjusting hyperparameters, training the model on a validation dataset, and evaluating its performance. Hyperparameters may include learning rates, regularization strengths, the number of hidden layers in a neural network, and more. The goal is to strike a balance between underfitting and overfitting—ensuring that the model neither learns the training data too closely nor fails to generalize to new data.
« Back to Glossary Index
