【《Python元学习实战》随书代码】’Hands-On-Meta-Learning-With-Python - Learning to Learn using One-Shot Learning, MAML, Reptile, Meta-SGD and more with Tensorflow by Sudharsan Ravichandiran
关于调整元学习的梯度
该存储库包含以下代码: ECCV 2020
与现有方法的比较:MAML,Meta-SGD和Ours。
请参考每个文件夹以完成不同的任务:分类,回归和RL。
引文
inproceedings{Christian2020ModGrad,
author = {Simon, Christian and Koniusz, Piotr and Nock, Richard and Harandi, Mehrtash},
title = {On Modulating the Gradi
On First-Order Meta-Learning Algorithms
Paper:https://arxiv.org/pdf/1803.02999.pdf
Code:https://github.com/openai/supervised-reptile
Tips:OpenAi的一篇相似MAML的Meta-learning相关的paper。
(阅读笔记)
1.Main idea
目标旨在实现相同分布的一类任务的少量样本快速学习。This paper considers meta-lea