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 1702.07664cs.CVcs.LG
收藏

ConvNets如何对非线性变换建模

How ConvNets model Non-linear Transformations

Carnegie Mellon University(卡内基梅隆大学)

Dipan K. Pal, Marios Savvides

摘要:

在本文中,我们从理论上解决了涉及深度卷积网络的三个基本问题,即不变性、深度和层次。我们介绍了转换网络(TN)的范式,它是卷积网络(ConvNets)的直接推广。从理论上讲,我们证明了TN(以及ConvNets)可以对输入的非线性变换保持不变,尽管仅在局部平移上进行了池化。我们的分析提供了清晰的见解,在这些网络的深度增加不变性。更深层次的网络能够模拟更丰富的转换类别。我们还发现,一个分层的架构允许网络生成不变性比非分层网络更有效。我们的研究结果为使用ConvNets的深度学习中的这三个基本问题提供了有用的见解。

英文摘要:

In this paper, we theoretically address three fundamental problems involving deep convolutional networks regarding invariance, depth and hierarchy. We introduce the paradigm of Transformation Networks (TN) which are a direct generalization of Convolutional Networks (ConvNets). Theoretically, we show that TNs (and thereby ConvNets) are can be invariant to non-linear transformations of the input despite pooling over mere local translations. Our analysis provides clear insights into the increase in invariance with depth in these networks. Deeper networks are able to model much richer classes of transformations. We also find that a hierarchical architecture allows the network to generate invariance much more efficiently than a non-hierarchical network. Our results provide useful insight into these three fundamental problems in deep learning using ConvNets.

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。

↑