Manual labels can be costly, slow to produce, or inconsistent. Self-supervised learning derives a training task from the data itself: the model predicts information that is available but hidden from it, reducing reliance on human-supplied labels. section 11.7
A self-supervised task can ask a model to predict:
- A missing portion of an image. section 11.7
- The next element in a sequence. section 11.7
- Content deliberately concealed from the model. section 11.7
The hidden content serves as the target against which a prediction is evaluated. This approach does not remove the need for data; it reduces the constraint imposed by manual labeling and can make larger training collections usable. It is one development in neural-network representation learning, alongside broad-data training of models that can later be adapted to related tasks. section 11.7 section 11.8









