Neuroevolution with Perceptron Turing Machines
This work addresses challenges in neuroevolution for researchers by providing a novel framework that integrates Turing machines, but it appears incremental as it builds on existing neuroevolution concepts with specific enhancements.
The authors tackled the problem of neuroevolution by introducing the perceptron Turing machine, which enables automatic scaling of solutions to larger problem sizes and allows for hand-coded solutions in a high-level language called Lopro, resulting in enhanced understanding of evolved solutions.
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.