Markov Brains: A Technical Introduction

TL;DR

Markov Brains are evolvable neural networks composed of interacting computational components, differing from traditional layered ANNs, with their structure and connections optimized through evolution.

Contribution

This paper provides a detailed technical introduction to Markov Brains, explaining their structure, functioning, and methods for studying and evolving them.

Findings

Markov Brains can be effectively evolved for complex tasks.

They differ structurally from conventional layered neural networks.

Techniques for analyzing and evolving Markov Brains are outlined.

Abstract

Markov Brains are a class of evolvable artificial neural networks (ANN). They differ from conventional ANNs in many aspects, but the key difference is that instead of a layered architecture, with each node performing the same function, Markov Brains are networks built from individual computational components. These computational components interact with each other, receive inputs from sensors, and control motor outputs. The function of the computational components, their connections to each other, as well as connections to sensors and motors are all subject to evolutionary optimization. Here we describe in detail how a Markov Brain works, what techniques can be used to study them, and how they can be evolved.