Probabilistic grammar-based deep neuroevolution

Pak-kan WONG, Man-leung WONG, Kwong-sak LEUNG

Research output: Book Chapters | Papers in Conference ProceedingsConference paper (refereed)Researchpeer-review

Abstract

Designing deep neural networks by human engineers can be challenging because there are various choices of deep neural network structures. We developed a deep neuroevolution system to automatically design deep neural network structures using deep neuroevolution. Our approach defines a set of structures using a probabilistic grammar and searches for best network structures using Probabilistic Model Building Genetic Programming. Our approach takes advantage of the probabilistic dependencies found among the structures of networks. The system was applied to tackle the problem of the physiological signal classification of abnormal heart rhythm. In the classification problem, our discovered model is more accurate than AlexNet. Our discovered model uses about 2% of the total amount of parameters of AlexNet.

Original languageEnglish
Title of host publicationGECCO 2019 Companion - Proceedings of the 2019 Genetic and Evolutionary Computation Conference Companion
Place of PublicationNew York
PublisherAssociation for Computing Machinery, Inc
Pages87-88
Number of pages2
ISBN (Electronic)9781450367486
ISBN (Print)9781450367486
DOIs
Publication statusPublished - 13 Jul 2019
Event2019 Genetic and Evolutionary Computation Conference, GECCO 2019 - Prague, Czech Republic
Duration: 13 Jul 201917 Jul 2019

Publication series

NameGECCO 2019 Companion - Proceedings of the 2019 Genetic and Evolutionary Computation Conference Companion

Conference

Conference2019 Genetic and Evolutionary Computation Conference, GECCO 2019
Abbreviated titleGECCO 19
CountryCzech Republic
CityPrague
Period13/07/1917/07/19

Fingerprint

Genetic programming
Engineers
Deep neural networks
Statistical Models

Keywords

  • Estimation of Distribution Programming
  • Deep Neural Network

Cite this

WONG, P., WONG, M., & LEUNG, K. (2019). Probabilistic grammar-based deep neuroevolution. In GECCO 2019 Companion - Proceedings of the 2019 Genetic and Evolutionary Computation Conference Companion (pp. 87-88). (GECCO 2019 Companion - Proceedings of the 2019 Genetic and Evolutionary Computation Conference Companion). New York: Association for Computing Machinery, Inc. https://doi.org/10.1145/3319619.3326778
WONG, Pak-kan ; WONG, Man-leung ; LEUNG, Kwong-sak. / Probabilistic grammar-based deep neuroevolution. GECCO 2019 Companion - Proceedings of the 2019 Genetic and Evolutionary Computation Conference Companion. New York : Association for Computing Machinery, Inc, 2019. pp. 87-88 (GECCO 2019 Companion - Proceedings of the 2019 Genetic and Evolutionary Computation Conference Companion).
@inproceedings{4a77e607d59b4ebca4631b734c5ed4ea,
title = "Probabilistic grammar-based deep neuroevolution",
abstract = "Designing deep neural networks by human engineers can be challenging because there are various choices of deep neural network structures. We developed a deep neuroevolution system to automatically design deep neural network structures using deep neuroevolution. Our approach defines a set of structures using a probabilistic grammar and searches for best network structures using Probabilistic Model Building Genetic Programming. Our approach takes advantage of the probabilistic dependencies found among the structures of networks. The system was applied to tackle the problem of the physiological signal classification of abnormal heart rhythm. In the classification problem, our discovered model is more accurate than AlexNet. Our discovered model uses about 2{\%} of the total amount of parameters of AlexNet.",
keywords = "Estimation of Distribution Programming, Deep Neural Network",
author = "Pak-kan WONG and Man-leung WONG and Kwong-sak LEUNG",
year = "2019",
month = "7",
day = "13",
doi = "10.1145/3319619.3326778",
language = "English",
isbn = "9781450367486",
series = "GECCO 2019 Companion - Proceedings of the 2019 Genetic and Evolutionary Computation Conference Companion",
publisher = "Association for Computing Machinery, Inc",
pages = "87--88",
booktitle = "GECCO 2019 Companion - Proceedings of the 2019 Genetic and Evolutionary Computation Conference Companion",

}

WONG, P, WONG, M & LEUNG, K 2019, Probabilistic grammar-based deep neuroevolution. in GECCO 2019 Companion - Proceedings of the 2019 Genetic and Evolutionary Computation Conference Companion. GECCO 2019 Companion - Proceedings of the 2019 Genetic and Evolutionary Computation Conference Companion, Association for Computing Machinery, Inc, New York, pp. 87-88, 2019 Genetic and Evolutionary Computation Conference, GECCO 2019, Prague, Czech Republic, 13/07/19. https://doi.org/10.1145/3319619.3326778

Probabilistic grammar-based deep neuroevolution. / WONG, Pak-kan; WONG, Man-leung; LEUNG, Kwong-sak.

GECCO 2019 Companion - Proceedings of the 2019 Genetic and Evolutionary Computation Conference Companion. New York : Association for Computing Machinery, Inc, 2019. p. 87-88 (GECCO 2019 Companion - Proceedings of the 2019 Genetic and Evolutionary Computation Conference Companion).

Research output: Book Chapters | Papers in Conference ProceedingsConference paper (refereed)Researchpeer-review

TY - GEN

T1 - Probabilistic grammar-based deep neuroevolution

AU - WONG, Pak-kan

AU - WONG, Man-leung

AU - LEUNG, Kwong-sak

PY - 2019/7/13

Y1 - 2019/7/13

N2 - Designing deep neural networks by human engineers can be challenging because there are various choices of deep neural network structures. We developed a deep neuroevolution system to automatically design deep neural network structures using deep neuroevolution. Our approach defines a set of structures using a probabilistic grammar and searches for best network structures using Probabilistic Model Building Genetic Programming. Our approach takes advantage of the probabilistic dependencies found among the structures of networks. The system was applied to tackle the problem of the physiological signal classification of abnormal heart rhythm. In the classification problem, our discovered model is more accurate than AlexNet. Our discovered model uses about 2% of the total amount of parameters of AlexNet.

AB - Designing deep neural networks by human engineers can be challenging because there are various choices of deep neural network structures. We developed a deep neuroevolution system to automatically design deep neural network structures using deep neuroevolution. Our approach defines a set of structures using a probabilistic grammar and searches for best network structures using Probabilistic Model Building Genetic Programming. Our approach takes advantage of the probabilistic dependencies found among the structures of networks. The system was applied to tackle the problem of the physiological signal classification of abnormal heart rhythm. In the classification problem, our discovered model is more accurate than AlexNet. Our discovered model uses about 2% of the total amount of parameters of AlexNet.

KW - Estimation of Distribution Programming

KW - Deep Neural Network

UR - http://www.scopus.com/inward/record.url?scp=85070656970&partnerID=8YFLogxK

U2 - 10.1145/3319619.3326778

DO - 10.1145/3319619.3326778

M3 - Conference paper (refereed)

SN - 9781450367486

T3 - GECCO 2019 Companion - Proceedings of the 2019 Genetic and Evolutionary Computation Conference Companion

SP - 87

EP - 88

BT - GECCO 2019 Companion - Proceedings of the 2019 Genetic and Evolutionary Computation Conference Companion

PB - Association for Computing Machinery, Inc

CY - New York

ER -

WONG P, WONG M, LEUNG K. Probabilistic grammar-based deep neuroevolution. In GECCO 2019 Companion - Proceedings of the 2019 Genetic and Evolutionary Computation Conference Companion. New York: Association for Computing Machinery, Inc. 2019. p. 87-88. (GECCO 2019 Companion - Proceedings of the 2019 Genetic and Evolutionary Computation Conference Companion). https://doi.org/10.1145/3319619.3326778