A Study of Fitness Landscapes for Neuroevolution
Created by W.Langdon from
gp-bibliography.bib Revision:1.7964
- @InProceedings{Rodrigues:2020:CEC,
-
author = "Nuno M. Rodrigues and Sara Silva and
Leonardo Vanneschi",
-
booktitle = "2020 IEEE Congress on Evolutionary Computation (CEC)",
-
title = "A Study of Fitness Landscapes for Neuroevolution",
-
year = "2020",
-
editor = "Yaochu Jin",
-
month = "19-24 " # jul,
-
keywords = "genetic algorithms, genetic programming",
-
isbn13 = "978-1-7281-6929-3",
-
DOI = "doi:10.1109/CEC48606.2020.9185783",
-
abstract = "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.",
-
notes = "Also known as \cite{9185783}",
- }
Genetic Programming entries for
Nuno Miguel Rodrigues Domingos
Sara Silva
Leonardo Vanneschi
Citations