Data augmentation

Technique used in machine learning and deep learning to increase the diversity of a training dataset without collecting new data. This is achieved by applying various transformations to the existing data, such as rotations, translations, scaling, flipping, and adding noise, which helps improve the robustness and generalization ability of models. Data augmentation is particularly beneficial for tasks involving image processing, text, and audio, and is aimed at preventing overfitting and enhancing model performance on unseen data.