论文标题
戴口罩：使用复发性神经切线内核的可变长度序列的压缩表示
Wearing a MASK: Compressed Representations of Variable-Length Sequences Using Recurrent Neural Tangent Kernels
论文作者
论文摘要
高维度对数据的使用构成了许多挑战，从可视化和解释到用于历史保存的预测和存储。降低固定长度序列的维度的技术丰富，但是这些方法很少将其推广到可变长度序列。为了解决这一差距，我们扩展了依赖内核通过使用复发性神经切线核（RNTK）的可变长度序列的现有方法。由于具有RELU激活的深神经网络是最大蛋白样条操作员（MASO），因此我们将方法配音Max-Affine样条线核（Mask）。我们演示了如何使用掩码扩展主组件分析（PCA）和T分布的随机邻居嵌入（T-SNE），并应用这些新算法以分离从二阶微分方程采样的合成时间序列数据。
High dimensionality poses many challenges to the use of data, from visualization and interpretation, to prediction and storage for historical preservation. Techniques abound to reduce the dimensionality of fixed-length sequences, yet these methods rarely generalize to variable-length sequences. To address this gap, we extend existing methods that rely on the use of kernels to variable-length sequences via use of the Recurrent Neural Tangent Kernel (RNTK). Since a deep neural network with ReLu activation is a Max-Affine Spline Operator (MASO), we dub our approach Max-Affine Spline Kernel (MASK). We demonstrate how MASK can be used to extend principal components analysis (PCA) and t-distributed stochastic neighbor embedding (t-SNE) and apply these new algorithms to separate synthetic time series data sampled from second-order differential equations.
