论文标题
用于序列建模的变分高RNN
Variational Hyper RNN for Sequence Modeling
论文作者
论文摘要
在这项工作中，我们提出了一个新型的概率序列模型，该模型在跨序列和单个序列内捕获时间序列数据的高变异性方面出色。我们的方法使用临时潜在变量来捕获有关基础数据模式的信息，并将潜在信息动态解码为基础解码器和经常性模型的权重的修改。该方法的疗效在一系列综合和现实世界的顺序数据上证明，这些数据表现出大规模变化，制度偏移和复杂的动力学。
In this work, we propose a novel probabilistic sequence model that excels at capturing high variability in time series data, both across sequences and within an individual sequence. Our method uses temporal latent variables to capture information about the underlying data pattern and dynamically decodes the latent information into modifications of weights of the base decoder and recurrent model. The efficacy of the proposed method is demonstrated on a range of synthetic and real-world sequential data that exhibit large scale variations, regime shifts, and complex dynamics.
