论文标题
卷积和完全连接的网络之间的计算分离
Computational Separation Between Convolutional and Fully-Connected Networks
论文作者
论文摘要
卷积神经网络（CNN）在众多计算机视觉任务中表现出无与伦比的性能。但是，从理论的角度来看，使用卷积网络而不是完全连接的网络的优点。在这项工作中，我们展示了卷积网络如何利用数据中的局部性，从而比完全连接的网络获得计算优势。具体而言，我们显示了一类问题，可以使用经过渐变味训练的卷积网络有效地解决这些问题，但同时很难使用多项式大小完全连接的网络学习。
Convolutional neural networks (CNN) exhibit unmatched performance in a multitude of computer vision tasks. However, the advantage of using convolutional networks over fully-connected networks is not understood from a theoretical perspective. In this work, we show how convolutional networks can leverage locality in the data, and thus achieve a computational advantage over fully-connected networks. Specifically, we show a class of problems that can be efficiently solved using convolutional networks trained with gradient-descent, but at the same time is hard to learn using a polynomial-size fully-connected network.
