理解MAML:Model-Agnostic Meta-Learning for Fast Adaption of Deep Networks
论文:Model-Agnostic Meta-Learning for Fast Adaptation of Deep Networks (arXiv:1703.03400v3 [cs.LG] 18 Jul 2017)MAML解决的就是few-shotlearning的问题。few-shot就是在有限的样本上训练后进行测试,那么问题转化为,用有限的样本进行训练使网络快速适应拟合当前的类别,然...
原创
2019-10-30 15:58:51 ·
1062 阅读 ·
0 评论