Catalog explanation
Self-supervised learning is valuable when unlabeled data is abundant because the model can learn useful representations before supervised fine-tuning.
AIF-C01 workspace
Bookmarks & Notes
A review desk for saved questions, notes, highlights, tags, filters, and next-review scheduling.
AIF-C01 catalog question
Modern Learning Paradigms
Which description best defines self-supervised learning?
Choose a saved item to pin a local review date.
A
The model creates proxy labels from unlabeled data, such as predicting masked tokens.
B
The model clusters records only by distance and never optimizes a predictive objective.