Glossary · Phase 4 · Deep learning
Backbone
The trained layers of a network that turn raw input into features; in transfer learning they're kept, frozen or fine-tuned, under a new head.
Try it now
Two questions decide it: how many labels you have, and how close the pretrained task is to yours.
Learn it properly
Transfer learning · Reuse a trained network: freeze the backbone, train a new head, fine-tune with two learning rates. About 40 minutes.
Other terms from the same lesson
- negative transfer: When features reused from another task make results worse than training from scratch, usually because the old task was too narrow or too different.
- parameter group: A set of a model's parameters that an optimizer updates with its own settings, such as a smaller learning rate for a pretrained backbone.
- transfer learning: Reusing a network trained on one task for another: keep its trained layers, replace the last one, and train with the new task's labels.
Never trained an AI?
Teach a small one to write, right in your browser. It takes about 20 seconds and needs no account.