# Self-Supervised Learning **Domain:** Machine Learning / Representation Learning **Doc Type:** Technical Concept Node **Maturity:** Developing **Related:** [[wiki/AI|AI]], [[wiki/Artificial Neural Networks|Artificial Neural Networks]], [[wiki/Yann LeCun|Yann LeCun]] --- ## Definition **Self-supervised learning** trains a system by deriving supervisory signals from the structure of the data itself rather than depending entirely on human-provided labels. Common objectives ask a model to predict masked, missing, transformed, or future portions of its input. ## Ontology Context This is a learning paradigm, not a model family or a claim about consciousness. It routes to [[wiki/Artificial Neural Networks|Artificial Neural Networks]] for implementation and to [[wiki/Mechanistic Intelligence|Mechanistic Intelligence]] when the corpus discusses learned internal structure as evidence that complex cognition can arise from trainable mechanisms. ## See Also [[wiki/Yann LeCun|Yann LeCun]] · [[wiki/Artificial Neural Networks|Artificial Neural Networks]] · [[wiki/Transformer Models|Transformer Models]] · [[wiki/Latent Space|Latent Space]]