Markov Brains: A Technical Introduction
Artificial Intelligence
2018-01-22 v1 Neurons and Cognition
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.
Keywords
Cite
@article{arxiv.1709.05601,
title = {Markov Brains: A Technical Introduction},
author = {Arend Hintze and Jeffrey A. Edlund and Randal S. Olson and David B. Knoester and Jory Schossau and Larissa Albantakis and Ali Tehrani-Saleh and Peter Kvam and Leigh Sheneman and Heather Goldsby and Clifford Bohm and Christoph Adami},
journal= {arXiv preprint arXiv:1709.05601},
year = {2018}
}