Deep Learning with PyTorch Quick Start Guide

Supervised learning

In supervised learning, a machine learning model is trained on a labeled dataset. Most successful deep learning models so far have been focused on supervised learning tasks. With supervised learning, each data instance (say, an image or an email), comes with two elements: a set of features, usually denoted as an uppercase X, and a label, denoted with a lower case, y. Sometimes, the label is called the target or answer. 

Supervised learning is usually conducted in two stages: a training phase when the model learns the characteristics of the data, and a testing phase, where predictions are made on unlabeled data. It is important that the model is trained and tested on separate datasets, since the goal is to generalize to ...