English

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

R2 v1 2026-06-23T01:42:45.104Z