arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 1807.05076cs.NEcs.AIcs.LGstat.ML
收藏

Hebbian快速权重元学习

Metalearning with Hebbian Fast Weights

Microsoft Research(微软研究院)

Tsendsuren Munkhdalai, Adam Trischler

摘要:

我们统一了最近的神经元方法一次性学习与旧的联想记忆模型的元学习的想法。我们的模型联合学习来表示数据,并将类标签绑定到Single Shot中的表示。它通过SGD跨任务学习的慢速权重构建表示,而通过Hebbian学习规则构建的快速权重为每个新任务实现一次性绑定。在Omniglot,Mini-ImageNet和Penn Treebank一次性学习基准测试中,我们的模型实现了最先进的结果。

英文摘要:

We unify recent neural approaches to one-shot learning with older ideas of associative memory in a model for metalearning. Our model learns jointly to represent data and to bind class labels to representations in a single shot. It builds representations via slow weights, learned across tasks through SGD, while fast weights constructed by a Hebbian learning rule implement one-shot binding for each new task. On the Omniglot, Mini-ImageNet, and Penn Treebank one-shot learning benchmarks, our model achieves state-of-the-art results.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑