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 1707.05841stat.MLcs.LG
收藏

线性时间复杂度的深度傅里叶散射网络及其对非线性不变量的扩展

Linear Time Complexity Deep Fourier Scattering Network and Extension to Nonlinear Invariants

Rice University(莱斯大学);AMU(艾克斯-马赛大学);University of Toulon(土伦大学);ENSAM(法国国立高等工程技术学校);CNRS(法国国家科学研究中心)

Randall Balestriero, Herve Glotin

摘要:

在本文中,我们提出了一个可扩展的版本的最先进的确定性时不变特征提取方法的基础上连续变化的基础和非线性,即散射网络。本文的第一个重点是扩展散射网络,允许使用高阶非线性,以及提取非线性和基于傅立叶的统计,导致任何固有结构化输入所需的不变量。为了达到快速卷积和利用小波的内在结构,我们在傅立叶域中推导出我们的完整模型。除了提供快速的计算,我们现在能够利用稀疏矩阵,由于非常高的稀疏性以及本地化的傅立叶域。因此,我们能够在傅立叶域中实现真正的线性时间复杂度,从而为机器学习任务提供快速且节能的解决方案。验证的功能和计算结果,将通过使用这些不变系数进行分类的音频记录的鸟类歌声捕获在多个不同的音景。最后,讨论了所提出的解决方案对深度人工神经网络的适用性。

英文摘要:

In this paper we propose a scalable version of a state-of-the-art deterministic time-invariant feature extraction approach based on consecutive changes of basis and nonlinearities, namely, the scattering network. The first focus of the paper is to extend the scattering network to allow the use of higher order nonlinearities as well as extracting nonlinear and Fourier based statistics leading to the required invariants of any inherently structured input. In order to reach fast convolutions and to leverage the intrinsic structure of wavelets, we derive our complete model in the Fourier domain. In addition of providing fast computations, we are now able to exploit sparse matrices due to extremely high sparsity well localized in the Fourier domain. As a result, we are able to reach a true linear time complexity with inputs in the Fourier domain allowing fast and energy efficient solutions to machine learning tasks. Validation of the features and computational results will be presented through the use of these invariant coefficients to perform classification on audio recordings of bird songs captured in multiple different soundscapes. In the end, the applicability of the presented solutions to deep artificial neural networks is discussed.

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。

↑