9 items
Supervised learning is the central paradigm of modern machine learning and deep learning.
Unsupervised learning studies data without explicit target labels. The dataset contains inputs only:
Self-supervised learning is a form of learning where the training signal is created from the data itself. The dataset does not need human-written labels, but the model still receives a prediction task.
Reinforcement learning studies how an agent learns to act through interaction with an environment.
A machine learning dataset is usually divided into three parts: a training set, a validation set, and a test set.
Bias and variance describe two different sources of prediction error. They are useful because they separate errors caused by an overly simple model from errors caused by an overly sensitive model.
Overfitting and underfitting describe two common ways a model can fail.
Evaluation metrics convert model behavior into numbers. A loss function guides training. A metric reports performance. Sometimes they are the same. Often they are different.
Data leakage occurs when information that should be unavailable during training or evaluation enters the modeling process. It causes performance estimates to look better than they really are.