A Study of Fitness Landscapes for Neuroevolution

01/30/2020
by   Nuno M. Rodrigues, et al.
20

Fitness landscapes are a useful concept to study the dynamics of meta-heuristics. In the last two decades, they have been applied with success to estimate the optimization power of several types of evolutionary algorithms, including genetic algorithms and genetic programming. However, so far they have never been used to study the performance of machine learning algorithms on unseen data, and they have never been applied to neuroevolution. This paper aims at filling both these gaps, applying for the first time fitness landscapes to neuroevolution and using them to infer useful information about the predictive ability of the method. More specifically, we use a grammar-based approach to generate convolutional neural networks, and we study the dynamics of three different mutations to evolve them. To characterize fitness landscapes, we study autocorrelation and entropic measure of ruggedness. The results show that these measures are appropriate for estimating both the optimization power and the generalization ability of the considered neuroevolution configurations.

READ FULL TEXT

page 1

page 2

page 3

page 4

05/08/2019

Learning to Evolve

Evolution and learning are two of the fundamental mechanisms by which li...
06/06/2023

Phylogeny-informed fitness estimation

Phylogenies (ancestry trees) depict the evolutionary history of an evolv...
07/15/2021

Death in Genetic Algorithms

Death has long been overlooked in evolutionary algorithms. Recent resear...
05/13/2022

Modularity in NEAT Reinforcement Learning Networks

Modularity is essential to many well-performing structured systems, as i...
09/06/2023

Fitness Approximation through Machine Learning

We present a novel approach to performing fitness approximation in genet...
03/09/2011

Integrated information increases with fitness in the evolution of animats

One of the hallmarks of biological organisms is their ability to integra...

Please sign up or login with your details

Forgot password? Click here to reset