arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2004.09222cs.LGstat.ML
收藏

神经常微分方程中的规范化

Towards Understanding Normalization in Neural ODEs

Skolkovo Institute of Science and Technology(斯科尔科沃科学技术研究所)

Julia Gusak, Larisa Markeeva, Talgat Daulbaev, Alexandr Katrutsa, Andrzej Cichocki, Ivan Oseledets

摘要:

规范化是深度学习中一种重要且广泛研究的技术。然而,它在基于常微分方程的网络(神经ODE)中的作用仍然知之甚少。本文研究了不同的归一化技术如何影响神经常微分方程的性能。特别是,我们证明了在CIFAR-10分类任务中可以达到93%的准确率,据我们所知,这是在这个问题上测试的神经ODE中报告的最高准确率。

英文摘要:

Normalization is an important and vastly investigated technique in deep learning. However, its role for Ordinary Differential Equation based networks (neural ODEs) is still poorly understood. This paper investigates how different normalization techniques affect the performance of neural ODEs. Particularly, we show that it is possible to achieve 93% accuracy in the CIFAR-10 classification task, and to the best of our knowledge, this is the highest reported accuracy among neural ODEs tested on this problem.

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。

↑