Semi-supervised Learning

An approach to machine learning that combines a small amount of labeled data with a large amount of unlabeled data during training. Semi-supervised learning falls between unsupervised learning (with no labeled training data) and supervised learning (with only labeled training data). Also note that active learning is a special form of semi-supervised learning.


Deep Semi-Supervised Learning
Discusses SSL in a deep learning setting and goes through some of the main deep learning SSL methods.
semi-supervised-learning code article paper
Active Learning: Curious AI Algorithms
Discover active learning, a case of semi-supervised machine learning: from its definition and its benefits, to applications and modern research into it.
semi-supervised-learning active-learning tutorial article
Semi-Supervised Learning in Computer Vision
A comprehensive overview of recent semi-supervised learning methods in Computer Vision
semi-supervised-learning computer-vision data-augmentation article
The Illustrated FixMatch for Semi-Supervised Learning
Learn how to leverage unlabeled data using FixMatch for semi-supervised learning
semi-supervised-learning computer-vision pytorch illustrated


What's new in semi-supervised learning? This paper, SimCLR, presents a new framework for contrastive learning of visual representations.
simclr semi-supervised-learning deep-learning machine-learning
Keras Debugging Tips
Four simple tips to help you debug your Keras code.
debugging tensorflow keras tutorial


Positive and Unlabeled Materials Machine Learning
PUMML is a code that uses semi-supervised machine learning to classify materials from only positive and unlabeled examples.
machine-learning semi-supervised-learning materials informatics
Bayesian Active Learning (BaaL)
BaaL is an active learning library by ElementAI. This repository contains techniques and reusable components to make active learning accessible for all.
active-learning bayesian-deep-learning baal elementai
Human in the Loop: Deep Learning without Wasteful Labelling
A new practical method for choosing batches of informative points in Deep Active Learning which avoids labelling redundancies that plague existing methods. ...
labeling active-learning bayesian-deep-learning bayesian-active-learning
Table of Contents
Share a project
Share something you or the community has made with ML.
Topic experts