Investigating Learning with Few Shot Data
Keyword(s):
In this project, I explore a teaching strategy called learning to teach (L2T) in which a teacher model could provide high-quality training samples to a student model. However, one major problem of L2T is that the teacher model will only select a subset of the training dataset as the final training data for the student. A learning to teach small-data learning strategy (L2TSDL) is proposed to solve this problem. In this strategy, the teacher model will calculate the importance score for every training sample and help student to make use of all training samples.
2015 ◽
Vol XL-3/W3
◽
pp. 427-431
◽
Keyword(s):
2021 ◽
Vol 16
(93)
◽
pp. 109-119
2018 ◽
Vol IV-2
◽
pp. 153-159
◽
Keyword(s):