Please use this identifier to cite or link to this item:
Full metadata record
DC FieldValueLanguage
dc.contributor.authorThomson, Sarah Len_UK
dc.contributor.authorOchoa, Gabrielaen_UK
dc.contributor.authorVeerapen, Nadarajenen_UK
dc.contributor.authorMichalak, Krzysztofen_UK
dc.description.abstractWe consider search spaces associated with neural network channel configuration. Architectures and their accuracy are visualised using low-dimensional Euclidean embedding (LDEE). Optimisation dynamics are captured using local optima networks (LONs). LONs are a compression of a fitness landscape: the nodes are local optima and the edges are search transitions between them. Several neural architecture search algorithms are tested on the search space and we discover that iterated local search (ILS) is a competitive algorithm for neural channel configuration. We additionally implement a landscape-aware ILS which performs well. Observations from the search and landscape space analyses bring visual clarity and insight to the science of neural network channel design: the results indicate that a high number of channels, kept constant throughout the network, is beneficial.en_UK
dc.relationThomson SL, Ochoa G, Veerapen N & Michalak K (2023) Channel Configuration for Neural Architecture: Insights from the Search Space. In: <i>TBC</i>. The Genetic and Evolutionary Computation Conference (GECCO) 2023, Lisbon, Portugal, 15.07.2023-19.07.2023. New York: ACM.
dc.rightsThis item has been embargoed for a period. During the embargo please use the Request a Copy feature at the foot of the Repository record to request a copy directly from the author. You can only request a copy if you wish to use this work for your own research or private study.en_UK
dc.subjectFitness Landscapesen_UK
dc.subjectNeural Architecture Searchen_UK
dc.subjectLocal Optima Net- works (LONs)en_UK
dc.titleChannel Configuration for Neural Architecture: Insights from the Search Spaceen_UK
dc.typeConference Paperen_UK
dc.rights.embargoreason[nas-gecco.pdf] Until this work is published there will be an embargo on the full text of this work.en_UK
dc.type.statusAM - Accepted Manuscripten_UK
dc.citation.conferencedates2023-07-15 - 2023-07-19en_UK
dc.citation.conferencelocationLisbon, Portugalen_UK
dc.citation.conferencenameThe Genetic and Evolutionary Computation Conference (GECCO) 2023en_UK
dc.publisher.addressNew Yorken_UK
dc.description.notesOutput Status: Forthcomingen_UK
dc.contributor.affiliationComputing Scienceen_UK
dc.contributor.affiliationComputing Scienceen_UK
dc.contributor.affiliationUniversité de Lilleen_UK
dc.contributor.affiliationWroclaw University of Economicsen_UK
rioxxterms.typeConference Paper/Proceeding/Abstracten_UK
local.rioxx.authorThomson, Sarah L|0000-0001-6971-7817en_UK
local.rioxx.authorOchoa, Gabriela|0000-0001-7649-5669en_UK
local.rioxx.authorVeerapen, Nadarajen|en_UK
local.rioxx.authorMichalak, Krzysztof|en_UK
local.rioxx.projectInternal Project|University of Stirling|
Appears in Collections:Computing Science and Mathematics Conference Papers and Proceedings

Files in This Item:
File Description SizeFormat 
nas-gecco.pdfFulltext - Accepted Version6.04 MBAdobe PDFUnder Embargo until 2025-03-31    Request a copy

This item is protected by original copyright

Items in the Repository are protected by copyright, with all rights reserved, unless otherwise indicated.

The metadata of the records in the Repository are available under the CC0 public domain dedication: No Rights Reserved

If you believe that any material held in STORRE infringes copyright, please contact providing details and we will remove the Work from public display in STORRE and investigate your claim.