An introduction to genetic algorithms
An introduction to genetic algorithms
Efficient evolution of neural networks through complexification
Efficient evolution of neural networks through complexification
Hi-index | 0.00 |
In the study of biological evolution, neutral theories are invoked by some researchers to explain the dynamics of evolving populations regardless of selection pressure. The current study compares the dynamics of speciation, extinction, and complexification in two sets of populations of evolving artificial neural networks. One set of populations evolved under selection pressure, their survival dependent upon performance at a control task, while the other set of populations had survivors chosen randomly. Despite predictions to the contrary, the results showed significant differences in all three dynamics, suggesting that neutral models are incomplete explanations at best and that selection pressure constrains evolutionary search in very specific ways.