论文标题
探索Kervolutional神经网络
Exploring Kervolutional Neural Networks
论文作者
论文摘要
在CVPR 2019会议上发表的一篇论文概述了一种新技术，称为“ Kervolution”，用于新型的增强卷积神经网络（CNN），称为“ Kervolutional神经网络”（KNN）。该论文断言，KNN比CNN获得更快的收敛性和更高的精度。此“迷你纸”将进一步研究原始论文中的发现，并对KNN建筑进行更深入的分析。这将通过分析超级参数（特别是学习率）对KNN与CNN的影响来实现，并尝试在原始论文中未测试的其他类型的Kervolution操作，这是对准确性和收敛时间和其他理论分析的更严格的统计分析。随附的代码公开可用。
A paper published in the CVPR 2019 conference outlines a new technique called 'kervolution' used in a new type of augmented convolutional neural network (CNN) called a 'kervolutional neural network' (KNN). The paper asserts that KNNs achieve faster convergence and higher accuracies than CNNs. This "mini paper" will further examine the findings in the original paper and perform a more in depth analysis of the KNN architecture. This will be done by analyzing the impact of hyper parameters (specifically the learning rate) on KNNs versus CNNs, experimenting with other types of kervolution operations not tested in the original paper, a more rigourous statistical analysis of accuracies and convergence times and additional theoretical analysis. The accompanying code is publicly available.
