发帖
雷达卡
How Important is the Train-Validation Split in Meta-Learning?
Yu Bai 1 Minshuo Chen 2 Pan Zhou 1 Tuo Zhao 2 Jason D. Lee 3 Sham Kakade 4
Huan Wang 1 Caiming Xiong 1
Abstract 1. Introduction
Meta-learning aims to perform fast adaptation Meta-learning, also known as “learning to learn”, has re-
on a new task through learning a “prior” from cently emerged as a powerful paradigm for learning to
multiple existing tasks. A ...
京公网安备 11010802022788号
