Genetic algorithms for evolving deep neural networks

Omid E. David; Iddo Greental

doi:10.1145/2598394.2602287

Genetic algorithms for evolving deep neural networks

Omid E. David
, Iddo Greental

Tel Aviv University

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution › peer-review

118 Scopus citations

Abstract

In recent years, deep learning methods applying unsupervised learning to train deep layers of neural networks have achieved remarkable results in numerous fields. In the past, many genetic algorithms based methods have been successfully applied to training neural networks. In this paper, we extend previous work and propose a GA-assisted method for deep learning. Our experimental results indicate that this GA-assisted approach improves the performance of a deep autoencoder, producing a sparser neural network.

Original language	English
Title of host publication	GECCO 2014 - Companion Publication of the 2014 Genetic and Evolutionary Computation Conference
Publisher	Association for Computing Machinery
Pages	1451-1452
Number of pages	2
ISBN (Print)	9781450328814
DOIs	https://doi.org/10.1145/2598394.2602287
State	Published - 2014
Event	16th Genetic and Evolutionary Computation Conference Companion, GECCO 2014 Companion - Vancouver, BC, Canada Duration: 12 Jul 2014 → 16 Jul 2014

Publication series

Name	GECCO 2014 - Companion Publication of the 2014 Genetic and Evolutionary Computation Conference

Conference

Conference	16th Genetic and Evolutionary Computation Conference Companion, GECCO 2014 Companion
Country/Territory	Canada
City	Vancouver, BC
Period	12/07/14 → 16/07/14

Keywords

Autoencoders
Deep learning
Genetic algorithms
Neural networks

Access to Document

10.1145/2598394.2602287

Cite this

David, O. E., & Greental, I. (2014). Genetic algorithms for evolving deep neural networks. In GECCO 2014 - Companion Publication of the 2014 Genetic and Evolutionary Computation Conference (pp. 1451-1452). (GECCO 2014 - Companion Publication of the 2014 Genetic and Evolutionary Computation Conference). Association for Computing Machinery. https://doi.org/10.1145/2598394.2602287

@inproceedings{56f3203b4b1b4664a1beb5619de15a94,

title = "Genetic algorithms for evolving deep neural networks",

abstract = "In recent years, deep learning methods applying unsupervised learning to train deep layers of neural networks have achieved remarkable results in numerous fields. In the past, many genetic algorithms based methods have been successfully applied to training neural networks. In this paper, we extend previous work and propose a GA-assisted method for deep learning. Our experimental results indicate that this GA-assisted approach improves the performance of a deep autoencoder, producing a sparser neural network.",

keywords = "Autoencoders, Deep learning, Genetic algorithms, Neural networks",

author = "David, \{Omid E.\} and Iddo Greental",

year = "2014",

doi = "10.1145/2598394.2602287",

language = "אנגלית",

isbn = "9781450328814",

series = "GECCO 2014 - Companion Publication of the 2014 Genetic and Evolutionary Computation Conference",

publisher = "Association for Computing Machinery",

pages = "1451--1452",

booktitle = "GECCO 2014 - Companion Publication of the 2014 Genetic and Evolutionary Computation Conference",

note = "16th Genetic and Evolutionary Computation Conference Companion, GECCO 2014 Companion ; Conference date: 12-07-2014 Through 16-07-2014",

}

David, OE & Greental, I 2014, Genetic algorithms for evolving deep neural networks. in GECCO 2014 - Companion Publication of the 2014 Genetic and Evolutionary Computation Conference. GECCO 2014 - Companion Publication of the 2014 Genetic and Evolutionary Computation Conference, Association for Computing Machinery, pp. 1451-1452, 16th Genetic and Evolutionary Computation Conference Companion, GECCO 2014 Companion, Vancouver, BC, Canada, 12/07/14. https://doi.org/10.1145/2598394.2602287

Genetic algorithms for evolving deep neural networks. / David, Omid E.; Greental, Iddo.
GECCO 2014 - Companion Publication of the 2014 Genetic and Evolutionary Computation Conference. Association for Computing Machinery, 2014. p. 1451-1452 (GECCO 2014 - Companion Publication of the 2014 Genetic and Evolutionary Computation Conference).

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution › peer-review

TY - GEN

T1 - Genetic algorithms for evolving deep neural networks

AU - David, Omid E.

AU - Greental, Iddo

PY - 2014

Y1 - 2014

N2 - In recent years, deep learning methods applying unsupervised learning to train deep layers of neural networks have achieved remarkable results in numerous fields. In the past, many genetic algorithms based methods have been successfully applied to training neural networks. In this paper, we extend previous work and propose a GA-assisted method for deep learning. Our experimental results indicate that this GA-assisted approach improves the performance of a deep autoencoder, producing a sparser neural network.

AB - In recent years, deep learning methods applying unsupervised learning to train deep layers of neural networks have achieved remarkable results in numerous fields. In the past, many genetic algorithms based methods have been successfully applied to training neural networks. In this paper, we extend previous work and propose a GA-assisted method for deep learning. Our experimental results indicate that this GA-assisted approach improves the performance of a deep autoencoder, producing a sparser neural network.

KW - Autoencoders

KW - Deep learning

KW - Genetic algorithms

KW - Neural networks

UR - https://www.scopus.com/pages/publications/84905653264

U2 - 10.1145/2598394.2602287

DO - 10.1145/2598394.2602287

M3 - ???researchoutput.researchoutputtypes.contributiontobookanthology.conference???

AN - SCOPUS:84905653264

SN - 9781450328814

T3 - GECCO 2014 - Companion Publication of the 2014 Genetic and Evolutionary Computation Conference

SP - 1451

EP - 1452

BT - GECCO 2014 - Companion Publication of the 2014 Genetic and Evolutionary Computation Conference

PB - Association for Computing Machinery

T2 - 16th Genetic and Evolutionary Computation Conference Companion, GECCO 2014 Companion

Y2 - 12 July 2014 through 16 July 2014

ER -

Genetic algorithms for evolving deep neural networks

Abstract

Publication series

Conference

Keywords

Access to Document

Other files and links

Fingerprint

Cite this