# Neuroevolution with Perceptron Turing Machines

## TL;DR

This paper presents perceptron Turing machines as a novel framework for neuroevolution, enabling scalable solutions, easier experimentation with hand-coded solutions, and improved interpretability of evolved systems.

## Contribution

It introduces perceptron Turing machines and a high-level language Lopro, enhancing neuroevolution's scalability, flexibility, and understanding of solutions.

## Key findings

- Automatic scaling to larger problem sizes
- Facilitation of hand-coded solution experimentation
- Potential for better understanding of evolved solutions

## Abstract

We introduce the perceptron Turing machine and show how it can be used to create a system of neuroevolution. Advantages of this approach include automatic scaling of solutions to larger problem sizes, the ability to experiment with hand-coded solutions, and an enhanced potential for understanding evolved solutions. Hand-coded solutions may be implemented in the low-level language of Turing machines, which is the genotype used in neuroevolution, but a high-level language called Lopro is introduced to make the job easier.