The term Semi-Supervised Learning originates from the fields of Artificial Intelligence, Big Data and Smart Data, as well as Digital Transformation. Semi-Supervised Learning means \u201epartially supervised learning\u201c in German and is a method by which computers can learn independently from data.<\/p>\n
Unlike conventional \u201eSupervised Learning\u201c, where all information (for example, thousands of photos of cats and dogs, all clearly labelled) is annotated by humans, Semi-Supervised Learning works with only a small amount of labelled data and a large amount of unlabelled data. This saves a lot of time and costs, as not every single image or piece of information needs to be reviewed by a human.<\/p>\n
A simple example: Imagine a company wants to automatically sort its emails into \u201espam\u201c and \u201enot spam\u201c. It only has 100 emails already marked as \u201espam\u201c or \u201enot spam\u201c, but thousands are still unmarked. Semi-supervised learning helps to analyse these unmarked emails and improve the categorisation by recognising patterns.<\/p>\n
This makes artificial intelligence more efficient and capable of making valuable decisions more quickly, even when little prepared data is available.<\/p>","protected":false},"excerpt":{"rendered":"