BriefGPT.xyz
Apr, 2019
Kervolution神经网络
Kervolutional Neural Networks
HTML
PDF
Chen Wang, Jianfei Yang, Lihua Xie, Junsong Yuan
TL;DR
本文介绍了一种新的 kervolution 运算，该方法可以在非线性空间内运行，扩展了卷积神经网络的模型容量，捕捉更高阶的特征交互，并通过基于补丁的核函数实现，而不引入额外参数。大量实验表明， kervolutional neural networks (KNN) 比基线卷积神经网络具有更高的准确性和更快的收敛速度。
Abstract
convolutional neural networks
(CNNs) have enabled the state-of-the-art performance in many computer vision tasks. However, little effort has been devoted to establishing convolution in
non-linear space
. Existing
→