Smoothing de Rótulos is a regularization technique usada em aprendizado de máquina, particularly in the training of redes neurais. It addresses the challenge of overfitting modificando a forma como os rótulos são representados no processo de treinamento.
Em métodos tradicionais de aprendizado supervisionado, each training example is assigned a hard label, which is often a one-hot encoded vector. For instance, if there are three classes, the label for class one would be represented as [1, 0, 0]. While this approach works well, it can lead to models that are overly confident in their predictions, resulting in poor generalization to new, unseen data.
Label smoothing alters this by softening the target labels. Instead of assigning a hard label of [1, 0, 0], label smoothing might adjust the label to [0.9, 0.05, 0.05]. This slight modification means that the model learns to distribute some probability mass over other classes, which encourages it to be less confident about its predictions. As a result, the model is better able to handle uncertainty and variations in the input data.
This technique has been shown to improve performance in various tasks, such as image classification and processamento de linguagem natural, especially when the training data is limited. By making the model less reliant on exact label matches, label smoothing can lead to improved robustness and accuracy in real-world applications.