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 2211.00396cs.LGeess.SP
收藏

小波神经网络与基于小波的神经网络

Wavelet Neural Networks versus Wavelet-based Neural Networks

Faculty of Engineering Science and Technology(工程科学与技术学院);UiT – The Arctic University of Norway(挪威北极大学)

Lubomir T. Dechevsky, Kristoffer M. Tangrand

摘要:

这是一系列研究中的第一篇论文,在这些研究中,我们引入了一种新型的神经网络(NN)--基于小波的神经网络(WBNN)--并研究了它们的特性和应用潜力。我们开始这项研究的比较,目前现有类型的小波神经网络(WNN),并表明WBNN大大优于WNN。WBNN的巨大优势的一个原因是它们基于双正交多分辨率分析(MRA)的高级层次树结构。另一个原因是实现了我们的新想法,将小波树深度纳入NN的神经宽度。小波深度和神经深度的角色的分离提供了一种概念上和算法上简单但高效的方法,用于群和深度WBNN的功能的急剧增加以及机器学习过程的快速加速。

英文摘要:

This is the first paper in a sequence of studies in which we introduce a new type of neural networks (NNs) -- wavelet-based neural networks (WBNNs) -- and study their properties and potential for applications. We begin this study with a comparison to the currently existing type of wavelet neural networks (WNNs) and show that WBNNs vastly outperform WNNs. One reason for the vast superiority of WBNNs is their advanced hierarchical tree structure based on biorthonormal multiresolution analysis (MRA). Another reason for this is the implementation of our new idea to incorporate the wavelet tree depth into the neural width of the NN. The separation of the roles of wavelet depth and neural depth provides a conceptually and algorithmically simple but highly efficient methodology for sharp increase in functionality of swarm and deep WBNNs and rapid acceleration of the machine learning process.

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。

↑