arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2302.13527eess.AScs.SDeess.SP
收藏

机器学习中用于改进泛化的复杂裁剪

Complex Clipping for Improved Generalization in Machine Learning

University of Washington(华盛顿大学);The Covid Detection Foundation DBA Virufy(新冠检测基金会(Virufy));The University of South Dakota(南达科他大学)

Les Atlas, Nicholas Rasmussen, Felix Schwock, Mert Pilanci

摘要:

对于许多机器学习应用程序,常见的输入表示是频谱图。频谱图的基本表示是给出复值的短时傅里叶变换(STFT)。频谱图使用这些复值的幅度,这是一种常用的检测器。现代机器学习系统通常是过度参数化的,其中可能的病态问题通过正则化得到改善。在深度网络的层之间通常使用整流线性单元(ReLU)激活函数已被证明有助于这种正则化,从而提高系统性能。我们将这种ReLU激活的想法扩展到复杂STFT的检测,提供了一个简单的计算修改和正则化的频谱图,这可能会导致更好的行为训练。然后,我们证实了这种方法的好处,在嘈杂的声学数据集用于现实世界的应用。泛化性能大幅提高。这种方法可能有益于使用时间-频率映射的其他应用,用于声学、音频和其他应用。

英文摘要:

For many machine learning applications, a common input representation is a spectrogram. The underlying representation for a spectrogram is a short time Fourier transform (STFT) which gives complex values. The spectrogram uses the magnitude of these complex values, a commonly used detector. Modern machine learning systems are commonly overparameterized, where possible ill-conditioning problems are ameliorated by regularization. The common use of rectified linear unit (ReLU) activation functions between layers of a deep net has been shown to help this regularization, improving system performance. We extend this idea of ReLU activation to detection for the complex STFT, providing a simple-to-compute modified and regularized spectrogram, which potentially results in better behaved training. We then confirmed the benefit of this approach on a noisy acoustic data set used for a real-world application. Generalization performance improved substantially. This approach might benefit other applications which use time-frequency mappings, for acoustic, audio, and other applications.

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。

↑