论文标题
使用本地因果状态的时空自动编码器
Spacetime Autoencoders Using Local Causal States
论文作者
论文摘要
局部因果状态是捕获复杂时空系统中有组织的模式和结构的潜在表示。我们扩大了它们的功能，将它们作为时空自动编码器构架。以前，它们仅被视为从可观察到的时空场到潜在局部因果状态领域的地图。在这里，我们表明有一个随机解码可以从潜在字段映射到可观察的字段。此外，他们的马尔可夫特性定义了潜在空间中的随机动态。结合随机解码，这为预测时空场提供了一种新方法。
Local causal states are latent representations that capture organized pattern and structure in complex spatiotemporal systems. We expand their functionality, framing them as spacetime autoencoders. Previously, they were only considered as maps from observable spacetime fields to latent local causal state fields. Here, we show that there is a stochastic decoding that maps back from the latent fields to observable fields. Furthermore, their Markovian properties define a stochastic dynamic in the latent space. Combined with stochastic decoding, this gives a new method for forecasting spacetime fields.
