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 1806.07528stat.MLcs.LG
收藏

多任务迁移学习中的不确定性

Uncertainty in Multitask Transfer Learning

Element AI;University of Montreal(蒙特利尔大学)

Alexandre Lacoste, Boris Oreshkin, Wonchang Chung, Thomas Boquet, Negar Rostamzadeh, David Krueger

摘要:

使用变分贝叶斯神经网络,我们开发了一种算法,能够积累知识到一个先验的多个不同的任务。其结果是一个丰富的和有意义的先验知识,能够对新任务进行Few-Shot学习。后验可以超越平均场近似,并产生良好的不确定性进行的实验。对玩具任务的分析表明,它可以从显著不同的任务中学习,同时发现它们之间的相似之处。Mini-Imagenet的实验在5次射击学习中获得了74.5%的准确率。最后,我们提供的实验表明,其他现有的方法可能无法在不同的基准表现良好。

英文摘要:

Using variational Bayes neural networks, we develop an algorithm capable of accumulating knowledge into a prior from multiple different tasks. The result is a rich and meaningful prior capable of few-shot learning on new tasks. The posterior can go beyond the mean field approximation and yields good uncertainty on the performed experiments. Analysis on toy tasks shows that it can learn from significantly different tasks while finding similarities among them. Experiments of Mini-Imagenet yields the new state of the art with 74.5% accuracy on 5 shot learning. Finally, we provide experiments showing that other existing methods can fail to perform well in different benchmarks.

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。

↑