Natural Evolution Speciation for NEAT
Document Type
Conference Proceeding
Publication Date
6-1-2019
Abstract
The Neural Evolution of Augmenting Topologies (NEAT) algorithm is a popular technique to evolve neural networks. While NEAT has been applied to many problems, such as control systems and game playing, the underlying speciation rules governing NEAT have not been explored. This paper proposes a new speciation technique, called Natural Evolution NEAT (NENEAT), that replaces NEAT's speciation strategy with a new stategy inspired by cladistics. The cladistic formation of species forms a tree of common descent. NENEAT can find smaller network solutions in fewer generation and population member evaluations than NEAT using the same number of children.
Source Publication
2019 IEEE Congress on Evolutionary Computation (CEC)
Recommended Citation
Knapp, Jon S. and Peterson, Gilbert L., "Natural Evolution Speciation for NEAT" (2019). Faculty Publications. 1956.
https://scholar.afit.edu/facpub/1956
