Speciation and diversity balance for genetic algorithms and application to structural neural network learning

Yong Wee Foo, Cindy Goh, Yun Li

Research output: Chapter in Book/Report/Conference proceedingConference contribution book

2 Citations (Scopus)

Abstract

Following analyzing existing challenges in addressing the balance between exploration and exploitation encountered by evolutionary algorithms, this paper develops a Genetic Algorithm with speciation (GASP). It first incorporates a novel encoding scheme and recombination method for a balanced genetic divergence when locating global optima in complex applications, such as structural and dynamic design of an artificial neural network (NN). GASP also addresses the problem of defining a measure and track population diversity whose NN structure is subjected to continual reorganization during the evolution process. Further, a novel approach to the neural network phenotype is developed, which maps it to a distinct genome with a variable length capable of fully representing the multilayer feed-forward NN structure. Using the concept generalized from linguistic complexity, the distance between strings can thus be derived from the single string and substring counts. The GASP is then applied to an NN design problem to forecast the energy consumption of a built environment. With the optimal NN structure, diversity is tracked and improved. The results show that the GASP succeeds in obtaining excellent accuracy and speed.

Original languageEnglish
Title of host publication2016 International Joint Conference on Neural Networks, IJCNN 2016
PublisherInstitute of Electrical and Electronics Engineers Inc.
Pages1283-1290
Number of pages8
Volume2016-October
DOIs
Publication statusPublished - 31 Oct 2016
Event2016 International Joint Conference on Neural Networks, IJCNN 2016 - Vancouver, Canada
Duration: 24 Jul 201629 Jul 2016

Conference

Conference2016 International Joint Conference on Neural Networks, IJCNN 2016
CountryCanada
CityVancouver
Period24/07/1629/07/16

Fingerprint

Genetic algorithms
Neural networks
Feedforward neural networks
Multilayer neural networks
Linguistics
Evolutionary algorithms
Energy utilization
Genes

Keywords

  • diversity
  • evolutionary computing
  • genetic algorithm
  • neural networks
  • speciation

Cite this

Foo, Y. W., Goh, C., & Li, Y. (2016). Speciation and diversity balance for genetic algorithms and application to structural neural network learning. In 2016 International Joint Conference on Neural Networks, IJCNN 2016 (Vol. 2016-October, pp. 1283-1290). [7727345] Institute of Electrical and Electronics Engineers Inc.. https://doi.org/10.1109/IJCNN.2016.7727345
Foo, Yong Wee ; Goh, Cindy ; Li, Yun. / Speciation and diversity balance for genetic algorithms and application to structural neural network learning. 2016 International Joint Conference on Neural Networks, IJCNN 2016. Vol. 2016-October Institute of Electrical and Electronics Engineers Inc., 2016. pp. 1283-1290
@inproceedings{b85752de24b146488f1341330d8b9555,
title = "Speciation and diversity balance for genetic algorithms and application to structural neural network learning",
abstract = "Following analyzing existing challenges in addressing the balance between exploration and exploitation encountered by evolutionary algorithms, this paper develops a Genetic Algorithm with speciation (GASP). It first incorporates a novel encoding scheme and recombination method for a balanced genetic divergence when locating global optima in complex applications, such as structural and dynamic design of an artificial neural network (NN). GASP also addresses the problem of defining a measure and track population diversity whose NN structure is subjected to continual reorganization during the evolution process. Further, a novel approach to the neural network phenotype is developed, which maps it to a distinct genome with a variable length capable of fully representing the multilayer feed-forward NN structure. Using the concept generalized from linguistic complexity, the distance between strings can thus be derived from the single string and substring counts. The GASP is then applied to an NN design problem to forecast the energy consumption of a built environment. With the optimal NN structure, diversity is tracked and improved. The results show that the GASP succeeds in obtaining excellent accuracy and speed.",
keywords = "diversity, evolutionary computing, genetic algorithm, neural networks, speciation",
author = "Foo, {Yong Wee} and Cindy Goh and Yun Li",
year = "2016",
month = "10",
day = "31",
doi = "10.1109/IJCNN.2016.7727345",
language = "English",
volume = "2016-October",
pages = "1283--1290",
booktitle = "2016 International Joint Conference on Neural Networks, IJCNN 2016",
publisher = "Institute of Electrical and Electronics Engineers Inc.",
address = "United States",

}

Foo, YW, Goh, C & Li, Y 2016, Speciation and diversity balance for genetic algorithms and application to structural neural network learning. in 2016 International Joint Conference on Neural Networks, IJCNN 2016. vol. 2016-October, 7727345, Institute of Electrical and Electronics Engineers Inc., pp. 1283-1290, 2016 International Joint Conference on Neural Networks, IJCNN 2016, Vancouver, Canada, 24/07/16. https://doi.org/10.1109/IJCNN.2016.7727345

Speciation and diversity balance for genetic algorithms and application to structural neural network learning. / Foo, Yong Wee; Goh, Cindy; Li, Yun.

2016 International Joint Conference on Neural Networks, IJCNN 2016. Vol. 2016-October Institute of Electrical and Electronics Engineers Inc., 2016. p. 1283-1290 7727345.

Research output: Chapter in Book/Report/Conference proceedingConference contribution book

TY - GEN

T1 - Speciation and diversity balance for genetic algorithms and application to structural neural network learning

AU - Foo, Yong Wee

AU - Goh, Cindy

AU - Li, Yun

PY - 2016/10/31

Y1 - 2016/10/31

N2 - Following analyzing existing challenges in addressing the balance between exploration and exploitation encountered by evolutionary algorithms, this paper develops a Genetic Algorithm with speciation (GASP). It first incorporates a novel encoding scheme and recombination method for a balanced genetic divergence when locating global optima in complex applications, such as structural and dynamic design of an artificial neural network (NN). GASP also addresses the problem of defining a measure and track population diversity whose NN structure is subjected to continual reorganization during the evolution process. Further, a novel approach to the neural network phenotype is developed, which maps it to a distinct genome with a variable length capable of fully representing the multilayer feed-forward NN structure. Using the concept generalized from linguistic complexity, the distance between strings can thus be derived from the single string and substring counts. The GASP is then applied to an NN design problem to forecast the energy consumption of a built environment. With the optimal NN structure, diversity is tracked and improved. The results show that the GASP succeeds in obtaining excellent accuracy and speed.

AB - Following analyzing existing challenges in addressing the balance between exploration and exploitation encountered by evolutionary algorithms, this paper develops a Genetic Algorithm with speciation (GASP). It first incorporates a novel encoding scheme and recombination method for a balanced genetic divergence when locating global optima in complex applications, such as structural and dynamic design of an artificial neural network (NN). GASP also addresses the problem of defining a measure and track population diversity whose NN structure is subjected to continual reorganization during the evolution process. Further, a novel approach to the neural network phenotype is developed, which maps it to a distinct genome with a variable length capable of fully representing the multilayer feed-forward NN structure. Using the concept generalized from linguistic complexity, the distance between strings can thus be derived from the single string and substring counts. The GASP is then applied to an NN design problem to forecast the energy consumption of a built environment. With the optimal NN structure, diversity is tracked and improved. The results show that the GASP succeeds in obtaining excellent accuracy and speed.

KW - diversity

KW - evolutionary computing

KW - genetic algorithm

KW - neural networks

KW - speciation

UR - http://www.scopus.com/inward/record.url?scp=85007188974&partnerID=8YFLogxK

U2 - 10.1109/IJCNN.2016.7727345

DO - 10.1109/IJCNN.2016.7727345

M3 - Conference contribution book

VL - 2016-October

SP - 1283

EP - 1290

BT - 2016 International Joint Conference on Neural Networks, IJCNN 2016

PB - Institute of Electrical and Electronics Engineers Inc.

ER -

Foo YW, Goh C, Li Y. Speciation and diversity balance for genetic algorithms and application to structural neural network learning. In 2016 International Joint Conference on Neural Networks, IJCNN 2016. Vol. 2016-October. Institute of Electrical and Electronics Engineers Inc. 2016. p. 1283-1290. 7727345 https://doi.org/10.1109/IJCNN.2016.7727345