arXivDaily arXiv每日学术速递 周一至周五更新
北美退伍军人节(Veterans Day),12 日无更新
arXiv 2201.07264cs.CV
收藏

探索卷积神经网络

Exploring Kervolutional Neural Networks

Carleton University(卡尔顿大学)

Nicolas Perez

摘要:

CVPR 2019会议上发表的一篇论文概述了一种名为“卷积”的新技术,用于一种新型的增强卷积神经网络(CNN),称为“卷积神经网络”(KNN)。该论文声称KNN比CNN实现更快的收敛和更高的精度。这篇“迷你论文”将进一步研究原始论文中的发现,并对KNN架构进行更深入的分析。这将通过分析超参数(特别是学习率)对KNN与CNN的影响,实验原始论文中未测试的其他类型的卷积运算,对精度和收敛时间进行更严格的统计分析以及额外的理论分析来完成。附带的代码是公开的。

英文摘要:

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.

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。

↑