Neural Tangent Transfer, or NTT, is a method for finding trainable sparse networks in a label-free manner. Specifically, NTT finds sparse networks whose training dynamics, as characterized by the neural tangent kernel, mimic those of dense networks in function space.
Source: Finding trainable sparse networks through Neural Tangent TransferPaper | Code | Results | Date | Stars |
---|
Component | Type |
|
---|---|---|
🤖 No Components Found | You can add them if they exist; e.g. Mask R-CNN uses RoIAlign |