Publication:
Training multimodal systems for classification with multiple objectives

cris.virtual.department#PLACEHOLDER_PARENT_METADATA_VALUE#
cris.virtual.department#PLACEHOLDER_PARENT_METADATA_VALUE#
cris.virtual.department#PLACEHOLDER_PARENT_METADATA_VALUE#
cris.virtual.departmentData Engineering
cris.virtual.department#PLACEHOLDER_PARENT_METADATA_VALUE#
cris.virtual.departmentbrowseData Engineering
cris.virtual.departmentbrowseData Engineering
cris.virtualsource.department#PLACEHOLDER_PARENT_METADATA_VALUE#
cris.virtualsource.department#PLACEHOLDER_PARENT_METADATA_VALUE#
cris.virtualsource.department#PLACEHOLDER_PARENT_METADATA_VALUE#
cris.virtualsource.department3a2553bc-4d23-4bae-a22f-5d92c868792c
cris.virtualsource.department#PLACEHOLDER_PARENT_METADATA_VALUE#
dc.contributor.authorArmitage, Jason
dc.contributor.authorThakur, Shramana
dc.contributor.authorTripathi, Rishi
dc.contributor.authorLehmann, Jens
dc.contributor.authorMaleshkova, Maria
dc.date.issued2020-01-01
dc.description.abstractWe learn about the world from a diverse range of sensory information. Automated systems lack this ability as investigation has centred on processing information presented in a single form. Adapting architectures to learn from multiple modalities creates the potential to learn rich representations of the world - but current multimodal systems only deliver marginal improvements on unimodal approaches. Neural networks learn sampling noise during training with the result that performance on unseen data is degraded. This research introduces a second objective over the multimodal fusion process learned with variational inference. Regularisation methods are implemented in the inner training loop to control variance and the modular structure stabilises performance as additional neurons are added to layers. This framework is evaluated on a multilabel classification task with textual and visual inputs to demonstrate the potential for multiple objectives and probabilistic methods to lower variance and improve generalisation.
dc.description.versionNA
dc.identifier.doi10.48550/arXiv.2008.11450
dc.identifier.issn1613-0073
dc.identifier.scopus2-s2.0-85091068389
dc.identifier.urihttps://openhsu.ub.hsu-hh.de/handle/10.24405/15234
dc.language.isoen
dc.relation.conference1st International Workshop on Cross-lingual Event-centric Open Analytics co-located with the 17th Extended Semantic Web Conference (ESWC 2020) Heraklion, Crete, Greece, June 3, 2020
dc.relation.journalCEUR Workshop Proceedings
dc.relation.orgunitUniversität Bonn
dc.rights.accessRightsmetadata only access
dc.subjectMachine Learning
dc.subjectMultimodal Data
dc.subjectProbabilistic Method
dc.titleTraining multimodal systems for classification with multiple objectives
dc.typeConference paper
dcterms.bibliographicCitation.booktitleCLEOPATRA 2020: cross-lingual event-centric open analytics : proceedings of the 1st International Workshop on Cross-lingual Event-centric Open Analytics
dcterms.bibliographicCitation.originalpublisherplaceHeraklion
dspace.entity.typePublication
hsu.peerReviewed
hsu.uniBibliographyNein
oaire.citation.endPage15
oaire.citation.startPage1
oaire.citation.volume2611
Files