Show simple item record

dc.contributor.authorAnders, Torsten
dc.contributor.authorInden, Benjamin
dc.date.accessioned2020-06-25T09:26:23Z
dc.date.available2019-12-16T00:00:00Z
dc.date.available2020-06-25T09:26:23Z
dc.date.issued2019-12-16
dc.identifier.citationAnders T, Inden B (2019) 'Machine learning of symbolic compositional rules with genetic programming: dissonance treatment in Palestrina', PeerJ Computer Science, 5 (e244 )en_US
dc.identifier.issn2376-5992
dc.identifier.doi10.7717/peerj-cs.244
dc.identifier.urihttp://hdl.handle.net/10547/624093
dc.description.abstractWe describe a method for automatically extracting symbolic compositional rules from music corpora. Resulting rules are expressed by a combination of logic and numeric relations, and they can therefore be studied by humans. These rules can also be used for algorithmic composition, where they can be combined with each other and with manually programmed rules. We chose genetic programming (GP) as our machine learning technique, because it is capable of learning formulas consisting of both logic and numeric relations. GP was never used for this purpose to our knowledge. We therefore investigate a well understood case in this study: dissonance treatment in Palestrina’s music. We label dissonances with a custom algorithm, automatically cluster melodic fragments with labelled dissonances into different dissonance categories (passing tone, suspension etc.) with the DBSCAN algorithm, and then learn rules describing the dissonance treatment of each category with GP. Learning is based on the requirement that rules must be broad enough to cover positive examples, but narrow enough to exclude negative examples. Dissonances from a given category are used as positive examples, while dissonances from other categories, melodic fragments without dissonances, purely random melodic fragments, and slight random transformations of positive examples, are used as negative examples.en_US
dc.language.isoenen_US
dc.publisherPeerJen_US
dc.relation.urlhttps://peerj.com/articles/cs-244/en_US
dc.rightsGreen - can archive pre-print and post-print or publisher's version/PDF
dc.rightsAttribution-NonCommercial-NoDerivatives 4.0 International*
dc.rights.urihttp://creativecommons.org/licenses/by-nc-nd/4.0/*
dc.subjectmachine learningen_US
dc.subjectmusic programmingen_US
dc.subjectSubject Categories::W390 Music not elsewhere classifieden_US
dc.titleMachine learning of symbolic compositional rules with genetic programming: dissonance treatment in Palestrinaen_US
dc.typeArticleen_US
dc.identifier.eissn2376-5992
dc.contributor.departmentUniversity of Bedfordshireen_US
dc.contributor.departmentNottingham Trent Universityen_US
dc.identifier.journalPeerJ Computer Scienceen_US
dc.date.updated2020-06-25T09:23:33Z
dc.description.noteopen access


Files in this item

Thumbnail
Name:
peerj-cs-244.pdf
Size:
2.133Mb
Format:
PDF

This item appears in the following Collection(s)

Show simple item record

Green - can archive pre-print and post-print or publisher's version/PDF
Except where otherwise noted, this item's license is described as Green - can archive pre-print and post-print or publisher's version/PDF