论文标题
增强非时系列数据的复发性神经切线内核
Enhanced Recurrent Neural Tangent Kernels for Non-Time-Series Data
论文作者
论文摘要
来自无限宽度政权中深神经网络（DNN）的内核不仅在一系列机器学习任务中提供了高性能，而且还提供了对DNN培训动态和概括的新理论见解。在本文中，我们将与复发性神经网络（RNN）相关的内核家族（以前仅用于简单的RNN）扩展到更复杂的体系结构，包括双向RNN和RNN，并具有平均池。我们还开发了快速的GPU实施，以利用内核的全部实际潜力。尽管通常仅将RNN应用于时间序列数据，但我们证明了使用基于RNN的内核的分类器优于UCI数据存储库中90个非时序数据集上的一系列基线方法。
Kernels derived from deep neural networks (DNNs) in the infinite-width regime provide not only high performance in a range of machine learning tasks but also new theoretical insights into DNN training dynamics and generalization. In this paper, we extend the family of kernels associated with recurrent neural networks (RNNs), which were previously derived only for simple RNNs, to more complex architectures including bidirectional RNNs and RNNs with average pooling. We also develop a fast GPU implementation to exploit the full practical potential of the kernels. Though RNNs are typically only applied to time-series data, we demonstrate that classifiers using RNN-based kernels outperform a range of baseline methods on 90 non-time-series datasets from the UCI data repository.
