Spacetime Autoencoders Using Local Causal States

10/12/2020
by   Adam Rupe, et al.
0

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.

READ FULL TEXT
POST COMMENT

Comments

There are no comments yet.

Authors

page 4

08/04/2020

Faithful Autoencoder Interpolation by Shaping the Latent Space

One of the fascinating properties of deep learning is the ability of the...
07/06/2021

Data-driven reduced order modeling of environmental hydrodynamics using deep autoencoders and neural ODEs

Model reduction for fluid flow simulation continues to be of great inter...
05/24/2017

Causal Effect Inference with Deep Latent-Variable Models

Learning individual-level causal effects from observational data, such a...
04/16/2021

Better Latent Spaces for Better Autoencoders

Autoencoders as tools behind anomaly searches at the LHC have the struct...
02/07/2022

CITRIS: Causal Identifiability from Temporal Intervened Sequences

Understanding the latent causal factors of a dynamical system from visua...
01/25/2019

Provably efficient RL with Rich Observations via Latent State Decoding

We study the exploration problem in episodic MDPs with rich observations...
01/03/2017

Semidefinite tests for latent causal structures

Testing whether a probability distribution is compatible with a given Ba...
This week in AI

Get the week's most popular data science and artificial intelligence research sent straight to your inbox every Saturday.