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 1803.08416cs.LGstat.ML
收藏

揭秘深度学习:迭代投影的几何方法

Demystifying Deep Learning: A Geometric Approach to Iterative Projections

North Carolina State University(北卡罗来纳州立大学);U.S. Army Research Office(美国陆军研究办公室)

Ashkan Panahi, Hamid Krim, Liyi Dai

摘要:

参数化学习方法,如深度学习(DL),在非线性回归中非常流行,尽管随着复杂性的增加(例如DL中的层数),它们的训练非常困难。在本文中,我们提出了一个替代的半参数框架,放弃了通常需要的反馈,通过引入几何正则化的新思想。我们表明,某些深度学习技术,如残差网络(ResNet)架构与我们的方法密切相关。因此,我们的技术可以用来分析这些类型的深度学习。此外,我们提出的初步结果证实,我们的方法可以很容易地训练,以获得复杂的结构。

英文摘要:

Parametric approaches to Learning, such as deep learning (DL), are highly popular in nonlinear regression, in spite of their extremely difficult training with their increasing complexity (e.g. number of layers in DL). In this paper, we present an alternative semi-parametric framework which foregoes the ordinarily required feedback, by introducing the novel idea of geometric regularization. We show that certain deep learning techniques such as residual network (ResNet) architecture are closely related to our approach. Hence, our technique can be used to analyze these types of deep learning. Moreover, we present preliminary results which confirm that our approach can be easily trained to obtain complex structures.

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。

↑