论文标题
稀疏的多户散射网络
Sparse Multi-Family Deep Scattering Network
论文作者
论文摘要
在这项工作中，我们提出了一种稀疏的多族深散射网络（SMF-DSN），这是一种利用深散射网络（DSN）的解释性并提高其表现力的新型体系结构。 DSN通过级联小波转换，复杂的模量并通过翻译不变的操作员提取数据表示，从而在信号中提取了显着和可解释的特征。首先，在过去几十年中利用高度专业的小波过滤器的开发，我们提出了一种多户住宅的DSN方法。特别是，我们建议在网络的每个层上跨多个小波变换，从而增加特征多样性并消除专家选择适当的滤波器的需求。其次，我们为DSN制定了适合DSN的最佳阈值策略，该策略正规化网络并控制信号引起的可能的不稳定性，例如非平稳噪声。我们的系统和原则性解决方案通过用作区分活动和噪声的局部掩码来使网络的潜在表示。 SMF-DSN通过（i）增加散射系数的多样性来增强DSN，并（ii）提高其相对于非平稳噪声的鲁棒性。
In this work, we propose the Sparse Multi-Family Deep Scattering Network (SMF-DSN), a novel architecture exploiting the interpretability of the Deep Scattering Network (DSN) and improving its expressive power. The DSN extracts salient and interpretable features in signals by cascading wavelet transforms, complex modulus and extract the representation of the data via a translation-invariant operator. First, leveraging the development of highly specialized wavelet filters over the last decades, we propose a multi-family approach to DSN. In particular, we propose to cross multiple wavelet transforms at each layer of the network, thus increasing the feature diversity and removing the need for an expert to select the appropriate filter. Secondly, we develop an optimal thresholding strategy adequate for the DSN that regularizes the network and controls possible instabilities induced by the signals, such as non-stationary noise. Our systematic and principled solution sparsifies the network's latent representation by acting as a local mask distinguishing between activity and noise. The SMF-DSN enhances the DSN by (i) increasing the diversity of the scattering coefficients and (ii) improves its robustness with respect to non-stationary noise.
