Show simple item record

dc.contributor.authorCai, Chenghao
dc.contributor.authorXu, Yanyan
dc.contributor.authorKe, Dengfeng
dc.contributor.authorSu, Kaile
dc.date.accessioned2021-01-13T00:13:43Z
dc.date.available2021-01-13T00:13:43Z
dc.date.issued2015
dc.identifier.issn1687-5265
dc.identifier.doi10.1155/2015/721367
dc.identifier.urihttp://hdl.handle.net/10072/400967
dc.description.abstractWe propose multistate activation functions (MSAFs) for deep neural networks (DNNs). These MSAFs are new kinds of activation functions which are capable of representing more than two states, including the N-order MSAFs and the symmetrical MSAF. DNNs with these MSAFs can be trained via conventional Stochastic Gradient Descent (SGD) as well as mean-normalised SGD. We also discuss how these MSAFs perform when used to resolve classification problems. Experimental results on the TIMIT corpus reveal that, on speech recognition tasks, DNNs with MSAFs perform better than the conventional DNNs, getting a relative improvement of 5.60% on phoneme error rates. Further experiments also reveal that mean-normalised SGD facilitates the training processes of DNNs with MSAFs, especially when being with large training sets. The models can also be directly trained without pretraining when the training set is sufficiently large, which results in a considerable relative improvement of 5.82% on word error rates.
dc.description.peerreviewedYes
dc.languageEnglish
dc.publisherHINDAWI LTD
dc.relation.ispartofpagefrom721367
dc.relation.ispartofjournalComputational Intelligence and Neuroscience
dc.relation.ispartofvolume2015
dc.subject.fieldofresearchNeurosciences
dc.subject.fieldofresearchCognitive Sciences
dc.subject.fieldofresearchcode1109
dc.subject.fieldofresearchcode1702
dc.subject.keywordsScience & Technology
dc.subject.keywordsLife Sciences & Biomedicine
dc.subject.keywordsMathematical & Computational Biology
dc.subject.keywordsNeurology
dc.titleDeep Neural Networks with Multistate Activation Functions
dc.typeJournal article
dc.type.descriptionC1 - Articles
dcterms.bibliographicCitationCai, C; Xu, Y; Ke, D; Su, K, Deep Neural Networks with Multistate Activation Functions, Computational Intelligence and Neuroscience, 2015, 2015, pp. 721367
dcterms.dateAccepted2015-08-23
dcterms.licensehttp://creativecommons.org/licenses/by/4.0/
dc.date.updated2021-01-13T00:10:38Z
dc.description.versionVersion of Record (VoR)
gro.rights.copyright© 2015 Chenghao Cai et al. This is an open access article distributed under the Creative Commons Attribution License, which permits unrestricted use, distribution, and reproduction in any medium, provided the original work is properly cited.
gro.hasfulltextFull Text
gro.griffith.authorSu, Kaile


Files in this item

This item appears in the following Collection(s)

  • Journal articles
    Contains articles published by Griffith authors in scholarly journals.

Show simple item record