Spacetime Autoencoders Using Local Causal States

Abstract

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.

References in corpus (5)

• Deep learning for universal linear embeddings of nonlinear dynamics
• Variational Encoding of Complex Dynamics
• Operator-theoretic framework for forecasting nonlinear time series with kernel analog techniques
• Local Causal States and Discrete Coherent Structures
• LICORS: Light Cone Reconstruction of States for Non-parametric Forecasting of Spatio-Temporal Systems

Cited by in corpus (1)

• Discovering Causal Structure with Reproducing-Kernel Hilbert Space $\epsilon$-Machines