Evolution strategies with an RBM-based meta-model

Makukhin, Kirill (2014). Evolution strategies with an RBM-based meta-model. In: Yang Sok Kim, Byeong Ho Kang and Deborah Richards, Knowledge management and acquisition for smart systems and services. 13th Pacific Rim Knowledge Acquisition Workshop, PKAW 2014, Gold Coast, QLD, Australia, (246-259). 1-2 December 2014. doi:10.1007/978-3-319-13332-4_20

Attached Files (Some files may be inaccessible until you login with your UQ eSpace credentials)
Name Description MIMEType Size Downloads

Author Makukhin, Kirill
Title of paper Evolution strategies with an RBM-based meta-model
Conference name 13th Pacific Rim Knowledge Acquisition Workshop, PKAW 2014
Conference location Gold Coast, QLD, Australia
Conference dates 1-2 December 2014
Proceedings title Knowledge management and acquisition for smart systems and services   Check publisher's open access policy
Journal name Knowledge Management and Acquisition for Smart Systems and Services, Pkaw 2014   Check publisher's open access policy
Series Lecture notes in computer science
Place of Publication Cham, Switzerland
Publisher Springer International Publishing
Publication Year 2014
Year available 2014
Sub-type Fully published paper
DOI 10.1007/978-3-319-13332-4_20
Open Access Status
ISBN 978-3-319-13331-7
ISSN 0302-9743
Editor Yang Sok Kim
Byeong Ho Kang
Deborah Richards
Volume 8863
Start page 246
End page 259
Total pages 14
Chapter number 20
Total chapters 22
Collection year 2015
Language eng
Abstract/Summary Evolution strategies have been demonstrated to offer a state-of- the-art performance on different optimisation problems. The efficiency of the algorithm largely depends on its ability to build an adequate meta-model of the function being optimised. This paper proposes a novel algorithm RBM-ES that utilises a computationally efficient restricted Boltzmann machine for maintaining the meta-model. We demonstrate that our algorithm is able to adapt its model to complex multidimensional landscapes. Furthermore, we compare the proposed algorithm to state-of the art algorithms such as CMA-ES on different tasks and demonstrate that the RBM-ES can achieve good performance.
Keyword Evolution strategies
Restricted Boltzmann machine
Surrogate model
Estimation of distribution algorithm
Q-Index Code E1
Q-Index Status Confirmed Code
Institutional Status UQ

Version Filter Type
Citation counts: TR Web of Science Citation Count  Cited 0 times in Thomson Reuters Web of Science Article
Scopus Citation Count Cited 0 times in Scopus Article
Google Scholar Search Google Scholar
Created: Fri, 17 Apr 2015, 12:53:44 EST by Caitlin Maskell on behalf of School of Information Technol and Elec Engineering