Markov Brains: A Technical Introduction
This presents a new paradigm for neural network design, potentially impacting researchers in evolutionary computation and artificial intelligence.
The paper introduces Markov Brains as a class of evolvable artificial neural networks that replace layered architectures with networks of individual computational components, and describes their operation, study techniques, and evolutionary optimization methods.
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.