Underfitting
Underfitting occurs when a machine learning model is too simple to capture the important patterns in its training data, resulting in poor performance on both training and unseen data.
What is Underfitting?
Underfitting happens when a model has insufficient complexity or has not been trained adequately to learn the relationships within the data. It may result from an overly simple model, insufficient training, excessive regularization, or features that do not provide enough useful information.
Why is Underfitting Important?
Underfitting limits a model's ability to make accurate predictions because it fails to learn enough from the available data. Identifying underfitting helps developers adjust model complexity, training duration, features, or hyperparameters to improve performance.
Common use cases
Underfitting is commonly evaluated during model training and validation for classification, regression, deep learning, and other machine learning tasks.