A Study of Fitness Landscapes for Neuroevolution

Nuno M. Rodrigues, Sara Silva, Leonardo Vanneschi

Research output: Chapter in Book/Report/Conference proceedingConference contributionpeer-review

2 Citations (Scopus)
2 Downloads (Pure)

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.

Original languageEnglish
Title of host publication2020 IEEE Congress on Evolutionary Computation, CEC 2020
Subtitle of host publicationConference Proceedings
PublisherInstitute of Electrical and Electronics Engineers Inc.
ISBN (Electronic)9781728169293
DOIs
Publication statusPublished - Jul 2020
Event2020 IEEE Congress on Evolutionary Computation, CEC 2020 - Virtual, Glasgow, United Kingdom
Duration: 19 Jul 202024 Jul 2020

Publication series

Name2020 IEEE Congress on Evolutionary Computation, CEC 2020 - Conference Proceedings

Conference

Conference2020 IEEE Congress on Evolutionary Computation, CEC 2020
CountryUnited Kingdom
CityVirtual, Glasgow
Period19/07/2024/07/20

Keywords

  • Autocorrelation
  • Convolutional Neural Networks
  • Entropic Measure of Ruggedness
  • Fitness Landscapes
  • Neuroevolution

Fingerprint Dive into the research topics of 'A Study of Fitness Landscapes for Neuroevolution'. Together they form a unique fingerprint.

Cite this