What term refers to a modeling error when a model learns training data too well, including its noise?

The term that describes a modeling error where the model learns the training data too well, including its noise, is known as overfitting. When a model is overfitted, it means that it has captured the complexities and fluctuations in the training data to an extent that it performs poorly on unseen data. This happens because the model has essentially memorized the training data rather than learning the underlying patterns, leading to high accuracy on the training set but poor generalization to new samples.

In contrast, other concepts like underfitting, generalization, and regularization do not describe this phenomenon accurately. Underfitting occurs when a model is too simple to capture the underlying trends in the data. Generalization refers to a model's ability to perform well on new, unseen data, which is what we strive for in machine learning. Regularization is a technique used to prevent overfitting by imposing additional constraints on the model to keep it simpler and more general. Thus, overfitting clearly defines the scenario of excessive learning from training data, making it the correct term in this context.