Modeling Dynamics with Deep Transition-Learning Networks

02/10/2018
by   David van Dijk, et al.
0

Markov processes, both classical and higher order, are often used to model dynamic processes, such as stock prices, molecular dynamics, and Monte Carlo methods. Previous works have shown that an autoencoder can be formulated as a specific type of Markov chain. Here, we propose a generative neural network known as a transition encoder, or transcoder, which learns such continuous-state dynamic processes. We show that the transcoder is able to learn both deterministic and stochastic dynamic processes on several systems. We explore a number of applications of the transcoder including generating unseen trajectories and examining the propensity for chaos in a dynamic system. Further, we show that the transcoder can speed up Markov Chain Monte Carlo (MCMC) sampling to a convergent distribution by training it to make several steps at a time. Finally, we show that the hidden layers of a transcoder are useful for visualization and salient feature extraction of the transition process itself.

READ FULL TEXT

Authors

page 5

page 6

10/07/2021

Curved Markov Chain Monte Carlo for Network Learning

We present a geometrically enhanced Markov chain Monte Carlo sampler for...
06/06/2018

Bayesian Inference for Diffusion Processes: Using Higher-Order Approximations for Transition Densities

A powerful tool in many areas of science, diffusion processes model rand...
06/24/2021

Abstraction of Markov Population Dynamics via Generative Adversarial Nets

Markov Population Models are a widespread formalism used to model the dy...
07/02/2018

A Piecewise Deterministic Markov Process via (r,θ) swaps in hyperspherical coordinates

Recently, a class of stochastic processes known as piecewise determinist...
05/09/2012

New inference strategies for solving Markov Decision Processes using reversible jump MCMC

In this paper we build on previous work which uses inferences techniques...
04/01/2010

A stochastic model of human visual attention with a dynamic Bayesian network

Recent studies in the field of human vision science suggest that the hum...
09/22/2016

Hawkes Processes with Stochastic Excitations

We propose an extension to Hawkes processes by treating the levels of se...
This week in AI

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