BriefGPT.xyz
Sep, 2018
一种用于定制模型训练的元学习方法
A Meta-Learning Approach for Custom Model Training
HTML
PDF
Amir Erfan Eshratifar, Mohammad Saeed Abrishami, David Eigen, Massoud Pedram
TL;DR
本文提出了一种联合训练方法，将迁移学习和元学习相结合，从而在少分类、少样本以及多分类、多样本任务中均可获得更好的泛化性能。
Abstract
transfer-learning
and
meta-learning
are two effective methods to apply knowledge learned from large data sources to new tasks. In
few-class
→