Open Access. Powered by Scholars. Published by Universities.®
- Institution
Articles 1 - 2 of 2
Full-Text Articles in Theory and Algorithms
Effective Ann Topologies For Use As Genotypes For Evaluating Design And Fabrication, John R. Peterson
Effective Ann Topologies For Use As Genotypes For Evaluating Design And Fabrication, John R. Peterson
Honors Theses
There is promise in the field of Evolutionary Design for systems that evolve not only what to manufacture but also how to manufacture it. EvoFab is a system that uses Genetic Algorithms to evolve Artificial Neural Networks (ANNs) which control a modified 3d-printer with the goal of automating some level of invention. ANNs are an obvious choice for use with a system like this as they are canonically evolvable encodings, and have been successfully used as evolved control systems in Evolutionary Robotics. However, there is little known about how the structural characteristics of an ANN affect the shapes that can …
Using Genetic Algorithms To Evolve Artificial Neural Networks, William T. Kearney
Using Genetic Algorithms To Evolve Artificial Neural Networks, William T. Kearney
Honors Theses
This paper demonstrates that neuroevolution is an effective method to determine an optimal neural network topology. I provide an overview of the NeuroEvolution of Augmenting Topologies (NEAT) algorithm, and describe how unique characteristics of this algorithm solve various problem inherent to neuroevolution (namely the competing conventions problem and the challenges associated with protecting topological innovation). Parallelization is shown to greatly speed up efficiency, further reinforcing neuroevolution as a potential alternative to traditional backpropagation. I also demonstrate that appropriate parameter selection is critical in order to efficiently converge to an optimal topology. Lastly, I produce an example solution to a medical …