Semi-Supervised Learning

Semi-Supervised Learning

Traditional machine learning (ML) divides the universe into algorithms that learn with a teacher (‘supervised learning’) and without a teacher (‘unsupervised learning’), but as is often the case, reality is a bit more complex.

Semi-supervised learning is one of the machine learning methods that has been gaining popularity in recent months. Companies like Google are enhancing tools for creating applications that utilise this algorithm. Imagine supervised learning as being somewhere in between unsupervised and supervised learning models. It’s akin to a teacher presenting a group of students with several examples and leaving the remaining examples for the students to complete as homework.

The aim of semi-supervised learning is to enable the training of ML models using a small labelled dataset alongside a large volume of unlabelled data.

A question for you: Do you ever use these algorithms in your practice?

Source: •

Originally published on Facebook — link to post