# Supervised learning Supervised learning is a machine learning approach in which a model is trained on labeled input-output pairs so that it can predict the correct output for new, unseen inputs. Supervised learning is a category of [machine-learning](https://www.wikiprompt.org/wiki/machine-learning) in which a model is trained on a dataset of examples that each pair an input with a known correct output, or label, and the model's objective is to learn a general mapping from inputs to outputs that generalizes to new, unseen examples. The word "supervised" refers to the fact that a labeled answer key, typically produced by human annotators or gathered from historical records, supervises the learning process by telling the model exactly what the correct answer should have been for each training example. ## Core tasks Supervised learning problems fall broadly into two categories. Classification tasks predict a discrete category, such as whether an email is spam, what object appears in an image, or what sentiment a review expresses. Regression tasks predict a continuous numerical value, such as a house price or a temperature forecast. Both are trained the same way: the model makes a prediction, a [loss-function](https://www.wikiprompt.org/wiki/loss-function) measures how far that prediction is from the true label, and [gradient-descent](https://www.wikiprompt.org/wiki/gradient-descent), computed via [backpropagation](https://www.wikiprompt.org/wiki/backpropagation) in the case of a [neural-network](https://www.wikiprompt.org/wiki/neural-network), adjusts the model's parameters to reduce that error, repeated over many examples and passes through the data. ## History Supervised learning predates deep learning by decades and includes classical algorithms such as linear and logistic regression, decision trees, support vector machines, developed and formalized in large part by Vladimir Vapnik, and k-nearest neighbors. The technique gained enormous momentum with the availability of large labeled datasets and cheap compute; the 2012 [ImageNet](https://www.wikiprompt.org/wiki/imagenet) competition, where [alexnet](https://www.wikiprompt.org/wiki/alexnet) dramatically outperformed prior methods on a large labeled image dataset, is widely credited with demonstrating that supervised deep learning could scale to outperform hand-engineered approaches, triggering the broader [deep-learning](https://www.wikiprompt.org/wiki/deep-learning) resurgence. ## Data and labeling Supervised learning's central practical bottleneck is the need for labeled data, which is often expensive and slow to produce, requiring human annotators to categorize, transcribe, or otherwise mark up large numbers of examples. This constraint motivated the development of alternative paradigms that reduce or eliminate the need for labels, including [unsupervised-learning](https://www.wikiprompt.org/wiki/unsupervised-learning), which finds structure in unlabeled data, and [self-supervised-learning](https://www.wikiprompt.org/wiki/self-supervised-learning), which generates its own training signal from unlabeled data, an approach that underlies the [pretraining](https://www.wikiprompt.org/wiki/pretraining) of modern [large language models](https://www.wikiprompt.org/wiki/large-language-model). Supervised learning remains essential at other stages of the modern AI pipeline, however, most notably in supervised [fine-tuning](https://www.wikiprompt.org/wiki/fine-tuning), where a pretrained model is adapted using labeled examples of desired input-output behavior, a step used in turning a base language model into an instruction-following assistant. ## Evaluation A model's performance in supervised learning is typically measured on a held-out test set that was not used during training, in order to estimate how well it generalizes rather than merely memorizing its training data, a failure mode called [overfitting](https://www.wikiprompt.org/wiki/overfitting). Common evaluation metrics include accuracy, precision, recall, and F1 score for classification, and mean squared error for regression, with the appropriate metric depending heavily on the task and the relative cost of different kinds of mistakes, such as false positives versus false negatives in a medical diagnosis setting. ## Significance and limitations Supervised learning has been the dominant paradigm behind most deployed machine learning systems for decades, from spam filters and credit scoring to medical image diagnosis and speech recognition. Its central limitation is a strict dependence on the quality and coverage of its labeled training data: a model can only be as good as its labels, and labels that reflect historical human bias or incomplete coverage of real-world scenarios will produce a model that inherits or amplifies those flaws, a concern central to research on [algorithmic-bias](https://www.wikiprompt.org/wiki/algorithmic-bias). As unlabeled and self-supervised approaches have matured, supervised learning has increasingly become one stage in a larger pipeline, rather than the entire training process for the most capable modern AI systems. --- Source: https://www.wikiprompt.org/wiki/supervised-learning License: CC BY-SA 4.0 (https://creativecommons.org/licenses/by-sa/4.0/) Last updated: 2026-09-02T20:28:58.567075+00:00