Deep Learning with PyTorch Quick Start Guide

Classification

Classification is probably the most common supervised machine learning task. There are several types of classification problems based the number of input and output labels. The task of a classification model is to find a pattern in the input features and associate this pattern with a label. A model should learn the distinguishing features of the data and then be able to predict the label of an unlabeled sample. The model essentially builds an inferred function from the training data. We will look at how this function is built shortly. We can distinguish three types of classification models:

• Binary classification: As in our toy—no toy example, this involves distinguishing between two labels.
• Multi-label classification: Involves ...