Learning to Teach with Deep Interactions

Cited by: 0|Bibtex|Views81
Other Links: arxiv.org

Abstract:

Machine teaching uses a meta/teacher model to guide the training of a student model (which will be used in real tasks) through training data selection, loss function design, etc. Previously, the teacher model only takes shallow/surface information as inputs (e.g., training iteration number, loss and accuracy from training/validation set...More

Code:

Data:

Full Text
Your rating :
0

 

Tags
Comments