Modular Meta-Learning with Shrinkage

Cited by: 5|Bibtex|Views36|Links

Abstract:

Most gradient-based approaches to meta-learning do not explicitly account for the fact that different parts of the underlying model adapt by different amounts when applied to a new task. For example, the input layers of an image classification convnet typically adapt very little, while the output layers can change significantly. This ca...More

Code:

Data:

Your rating :
0

 

Tags
Comments