This HTML5 document contains 32 embedded RDF statements represented using HTML+Microdata notation.

The embedded RDF content will be recognized by any processor of HTML5 Microdata.

Namespace Prefixes

PrefixIRI
n12doi:10.1007/
dctermshttp://purl.org/dc/terms/
n2https://kar.kent.ac.uk/id/eprint/
wdrshttp://www.w3.org/2007/05/powder-s#
dchttp://purl.org/dc/elements/1.1/
n8http://purl.org/ontology/bibo/status/
n20https://kar.kent.ac.uk/id/subject/
rdfshttp://www.w3.org/2000/01/rdf-schema#
n16https://demo.openlinksw.com/about/id/entity/https/raw.githubusercontent.com/annajordanous/CO644Files/main/
n14https://kar.kent.ac.uk/id/eprint/78198#
n5http://eprints.org/ontology/
n10https://kar.kent.ac.uk/78198/
n17http://www.loc.gov/loc.terms/relators/
n4https://kar.kent.ac.uk/id/event/
bibohttp://purl.org/ontology/bibo/
n19https://kar.kent.ac.uk/id/publication/
n21https://kar.kent.ac.uk/id/org/
rdfhttp://www.w3.org/1999/02/22-rdf-syntax-ns#
owlhttp://www.w3.org/2002/07/owl#
n6https://kar.kent.ac.uk/id/document/
n22https://kar.kent.ac.uk/id/
xsdhhttp://www.w3.org/2001/XMLSchema#
n23https://demo.openlinksw.com/about/id/entity/https/www.cs.kent.ac.uk/people/staff/akj22/materials/CO644/
n18https://kar.kent.ac.uk/id/person/

Statements

Subject Item
n2:78198
rdf:type
bibo:AcademicArticle bibo:Article n5:ConferenceItemEPrint n5:EPrint
rdfs:seeAlso
n10:
owl:sameAs
n12:978-3-030-34885-4_4
n17:EDT
n18:ext-2666cec85f61b15292ba696071da0eb2 n18:ext-1702185e1e3e57af1dcfde37828a0a57
n5:hasAccepted
n6:3192902
n5:hasDocument
n6:3192902 n6:3192903 n6:3192922 n6:3192923 n6:3192924 n6:3192925
dc:hasVersion
n6:3192902
dcterms:title
Stepwise Evolutionary Learning using Deep Learned Guidance Functions
wdrs:describedby
n16:export_kar_RDFN3.n3 n23:export_kar_RDFN3.n3
dcterms:date
2019-11-19
dcterms:creator
n18:ext-c.g.johnson@kent.ac.uk
bibo:status
n8:peerReviewed n8:published
dcterms:publisher
n21:ext-1c5ddec173ca8cdfba8b274309638579
bibo:abstract
This paper explores how Learned Guidance Functions (LGFs)— a pre-training method used to smooth search landscapes—can be used as a fitness function for evolutionary algorithms. A new form of LGF is introduced, based on deep neural network learning, and it is shown how this can be used as a fitness function. This is applied to a test problem: unscrambling the Rubik’s Cube. Comparisons are made with a previous LGF approach based on random forests, and with a baseline approach based on traditional error-based fitness.
dcterms:isPartOf
n19:ext-03029743 n22:repository
dcterms:subject
n20:QA76.87
bibo:authorList
n14:authors
bibo:editorList
n14:editors
bibo:presentedAt
n4:ext-fa08d1b6e44add24fbe1268f67ba3b00
bibo:volume
11927