Picture of Yee Wei Law

Few-shot learning

by Yee Wei Law - Thursday, 16 February 2023, 3:29 PM
 
Definition 1: Few-shot learning [WYKN20, Definition 2.2]

A type of machine learning problems (specified by experience , task and performance measure ), where contains only a limited number of examples with supervised information for .

References

[] .
[WYKN20] Y. Wang, Q. Yao, J. T. Kwok, and L. M. Ni, Generalizing from a few examples: A survey on few-shot learning, ACM Comput. Surv. 53 no. 3 (2020). https://doi.org/10.1145/3386252.

» Artificial intelligence (including machine learning which includes deep learning)