Markov Chain Neural Networks
Machine Learning
2018-05-03 v1 Machine Learning
Abstract
In this work we present a modified neural network model which is capable to simulate Markov Chains. We show how to express and train such a network, how to ensure given statistical properties reflected in the training data and we demonstrate several applications where the network produces non-deterministic outcomes. One example is a random walker model, e.g. useful for simulation of Brownian motions or a natural Tic-Tac-Toe network which ensures non-deterministic game behavior.
Keywords
Cite
@article{arxiv.1805.00784,
title = {Markov Chain Neural Networks},
author = {Maren Awiszus and Bodo Rosenhahn},
journal= {arXiv preprint arXiv:1805.00784},
year = {2018}
}
Comments
Accepted for CVPR 2018 Workshop Track