AIExplainer
Machine Learning Intermediate 2 min read

What is semi-supervised learning?

A machine learning approach that uses a combination of labeled and unlabeled data to train models

Semi-supervised learning is a type of machine learning that uses both labeled data, where the correct output is already known, and unlabeled data, where the correct output is not known, to train models. This approach is useful when labeled data is scarce or expensive to obtain, but unlabeled data is abundant.

Think of semi-supervised learning like learning a new language. Imagine you have a few language lessons with a teacher who corrects your mistakes (labeled data), but you also spend a lot of time reading books and listening to podcasts in the new language without any corrections (unlabeled data). Over time, you'll learn to understand and speak the language better, even with limited teacher guidance.

Self-driving cars use semi-supervised learning to improve their ability to recognize objects on the road. They can be trained on a small set of labeled images of pedestrians, cars, and road signs, and a large set of unlabeled images from cameras and sensors.

Semi-supervised learning is used in applications such as image classification, natural language processing, and speech recognition, where large amounts of unlabeled data are available, but labeling all of it would be impractical or too expensive.

One common misconception is that semi-supervised learning is the same as unsupervised learning, but it's not. Semi-supervised learning still uses some labeled data to guide the learning process, whereas unsupervised learning relies solely on unlabeled data.

Semi-supervised learning has been an active area of research since the 1990s, with early work focusing on methods such as self-training and co-training. In recent years, deep learning techniques have been applied to semi-supervised learning, leading to significant improvements in performance.

partially supervised learning weakly supervised learning

Three products for different needs — explore what’s relevant to you.