AI glossary · Machine learning
Self-supervised learning
Self-supervised learning is when an AI model creates its own practice questions from raw data, like hiding a word in a sentence and learning to predict it.
In more detail
Because the answers come from the data itself, there’s no need for people to label millions of examples. That makes it possible to learn from enormous amounts of text, images or audio.
It is how large language models are pre-trained: predicting the next word over and over.
Related terms
Pre-trainingPre-training is the first, biggest stage of training an AI model, where it learns general patterns from a huge dataset before being adapted for specific uses.Unsupervised learningUnsupervised learning finds patterns and groups in data that has no labels, such as discovering types of customers from their shopping habits.Supervised learningSupervised learning trains an AI model on examples that come with the right answer, such as photos labelled “cat” or “dog”, so it can label new examples.Large language model (LLM)A large language model (LLM) is an AI model trained on vast amounts of text to understand and generate language. It powers chatbots like ChatGPT.
Browse related tools
AI tools listed on BroUseAI in these categories.
