SelfSupervisedLearning.md (470B)
1 # Self-supervised learning (SSL) 2 3 ML CH1 4 5 **Definition:** Self-supervised learning is the process of chaning input data and the model predicting the output where the output is known to it. 6 7 This is similar to [SemiSupervisedLearning](SemiSupervisedLearning.md) where models are trained to detect certain information (clustering) without knowing what the information means. 8 9 Basically, the model learns to train itself. By messing with inputs to get expected outputs.