Supervised, Semi-Supervised, Unsupervised, and Self-Supervised Learning

Demystifying each learning task

The exponential number of research and publications have introduced many terms and concepts in the domain of machine learning, yet a number of them have degenerated to merely buzzwords without people fully understanding their differences.

This article demystifies the four core regimes in the field of machine learning — supervised, semi-supervised, unsupervised, and self-supervised learning — and discusses several examples/methods in solving these problems. Enjoy!

Supervised Learning

Figure 1. Illustration of Supervised Learning. Image made by author with resources from Unsplash.

The most common, and perhaps THE type that we refer to when talking about machine learning is supervised learning.

In simple words, supervised learning provides a set of input-output pairs such that we can learn an intermediate system that maps inputs to correct outputs.

A naive example of supervised learning is determining the class (i.e., dogs/cats, etc) of an image based on a dataset of images and their corresponding classes, which we will refer to as their labels.

With the given input-label pair, the current popular approach will be to directly train a deep neural network (i.e., a convolutional neural network) to output a…