Please use this identifier to cite or link to this item:
Appears in Collections:Computing Science and Mathematics Conference Papers and Proceedings
Author(s): Thomson, Sarah L
Ochoa, Gabriela
Veerapen, Nadarajen
Michalak, Krzysztof
Contact Email:
Title: Channel Configuration for Neural Architecture: Insights from the Search Space
Citation: Thomson 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.
Date Deposited: 8-Apr-2023
Conference Name: The Genetic and Evolutionary Computation Conference (GECCO) 2023
Conference Dates: 2023-07-15 - 2023-07-19
Conference Location: Lisbon, Portugal
Abstract: We 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.
Status: AM - Accepted Manuscript
Rights: This 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.

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

Note: If any of the files in this item are currently embargoed, you can request a copy directly from the author by clicking the padlock icon above. However, this facility is dependent on the depositor still being contactable at their original email address.

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.