DAE-GP: denoising autoencoder LSTM networks as probabilistic models in estimation of distribution genetic programming

Publikationstyp:
Konferenzbeitrag
Metadaten:
Autoren
Autoren-URL
https://www.webofscience.com/api/gateway?GWVersion=2&SrcApp=fis-test-1&SrcAuth=WosAPI&KeyUT=WOS:000605292300120&DestLinkType=FullRecord&DestApp=WOS_CPL
DOI
10.1145/3377930.3390180
Externe Identifier
  • Clarivate Analytics Document Solution ID: BQ5JD
Zeitschrift
GECCO'20: PROCEEDINGS OF THE 2020 GENETIC AND EVOLUTIONARY COMPUTATION CONFERENCE
Schlüsselwörter
  • Genetic Programming
  • Estimation of Distribution Algorithms
  • Denoising Autoencoders
  • Long Short-Term Memory Networks
Paginierung
1037 - 1045
Datum der Veröffentlichung
2020
Status
Published
Titel
DAE-GP: Denoising Autoencoder LSTM Networks as Probabilistic Models in Estimation of Distribution Genetic Programming

Datenquelle: Web of Science (Lite)

Andere Metadatenquellen:
Autoren
DOI
10.1145/3377930.3390180
Zeitschrift
Proceedings of the 2020 Genetic and Evolutionary Computation Conference
Name of conference
GECCO '20: Genetic and Evolutionary Computation Conference
Online publication date
2020
Datum der Veröffentlichung
2020
Status
Published
Herausgeber
ACM
Herausgeber URL
http://dx.doi.org/10.1145/3377930.3390180
Datum der Datenerfassung
2023
Titel
DAE-GP

Datenquelle: Crossref

Autoren
Editoren
  • Carlos Artemio Coello Coello
ISBN-13
978-1-4503-7128-5
Zeitschrift
GECCO
Paginierung
1037 - 1045
Datum der Veröffentlichung
2020
Herausgeber
ACM
Herausgeber URL
https://doi.org/10.1145/3377930
Titel
DAE-GP: denoising autoencoder LSTM networks as probabilistic models in estimation of distribution genetic programming.

Datenquelle: DBLP

Abstract
Estimation of distribution genetic programming (EDA-GP) algorithms are metaheuristics where sampling new solutions from a learned probabilistic model replaces the standard mutation and recombination operators of genetic programming (GP). This paper presents DAE-GP, a new EDA-GP which uses denoising autoencoder long short-term memory networks (DAE-LSTMs) as probabilistic model. DAE-LSTMs are artificial neural networks that first learn the properties of a parent population by mapping promising candidate solutions to a latent space and reconstructing the candidate solutions from the latent space. The trained model is then used to sample new offspring solutions. We show on a generalization of the royal tree problem that DAE-GP outperforms standard GP and that performance differences increase with higher problem complexity. Furthermore, DAE-GP is able to create offspring with higher fitness from a learned model in comparison to standard GP. We believe that the key reason for the high performance of DAE-GP is that we do not impose any assumptions about the relationships between learned variables which is different to previous EDA-GP models. Instead, DAE-GP flexibly identifies and models relevant dependencies of promising candidate solutions.
Autoren
DOI
10.1145/3377930.3390180
Conference finish date
2020
ISBN-13
9781450371285
Zeitschrift
Proceedings of the 2020 Genetic and Evolutionary Computation Conference
Conference place
Cancún, Mexiko
Name of conference
GECCO '20: Genetic and Evolutionary Computation Conference
Online publication date
2020
Paginierung
1037 - 1045, 9
Datum der Veröffentlichung
2020
Herausgeber
ACM
Herausgeber URL
https://dl.acm.org/doi/10.1145/3377930.3390180?cid=81100197550
Datum der Datenerfassung
2020
Conference start date
2020
Titel
DAE-GP: denoising autoencoder LSTM networks as probabilistic models in estimation of distribution genetic programming

Datenquelle: Manual

Beziehungen:
Eigentum von

Werkzeuge