Markov Chain Neural Networks

TL;DR

This paper introduces a neural network model designed to simulate Markov Chains, capable of generating non-deterministic outcomes and reflecting statistical properties of training data for applications like random walks and game simulations.

Contribution

It presents a novel neural network architecture that can express, train, and ensure Markov Chain properties, enabling non-deterministic simulations in various applications.

Findings

Successfully models Markov Chain behaviors

Produces non-deterministic outcomes in simulations

Ensures statistical properties in training data

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.