BriefGPT.xyz
Mar, 2017
元网络
Meta Networks
HTML
PDF
Tsendsuren Munkhdalai, Hong Yu
TL;DR
本文介绍了一种新的元学习方法Meta Networks(MetaNet),它通过快速参数化学习跨任务的元级知识,并在新概念上进行快速泛化,同时保持了以前所学的性能表现,在Omniglot和Mini-ImageNet基准测试中,我们的MetaNet模型实现了接近人类水平的表现,并在准确性上优于基线方法高达6%。我们展示了MetaNet的几个有吸引力的性质,如泛化和持续学习。
Abstract
Deep
neural networks
have been successfully applied in applications with a large amount of labeled data. However, there are major drawbacks of the
neural networks
that are related to
→