ub.xmlui.mirage2.page-structure.muninLogoub.xmlui.mirage2.page-structure.openResearchArchiveLogo
    • EnglishEnglish
    • norsknorsk
  • Velg spraakEnglish 
    • EnglishEnglish
    • norsknorsk
  • Administration/UB
View Item 
  •   Home
  • Fakultet for naturvitenskap og teknologi
  • Institutt for fysikk og teknologi
  • Artikler, rapporter og annet (fysikk og teknologi)
  • View Item
  •   Home
  • Fakultet for naturvitenskap og teknologi
  • Institutt for fysikk og teknologi
  • Artikler, rapporter og annet (fysikk og teknologi)
  • View Item
JavaScript is disabled for your browser. Some features of this site may not work without it.

The deep kernelized autoencoder

Permanent link
https://hdl.handle.net/10037/16437
DOI
https://doi.org/10.1016/j.asoc.2018.07.029
Thumbnail
View/Open
article.pdf (5.038Mb)
Accepted manuscript version (PDF)
Date
2018-07-18
Type
Journal article
Tidsskriftartikkel
Peer reviewed

Author
Kampffmeyer, Michael C.; Løkse, Sigurd; Bianchi, Filippo Maria; Jenssen, Robert; Livi, Lorenzo
Abstract
Autoencoders learn data representations (codes) in such a way that the input is reproduced at the output of the network. However, it is not always clear what kind of properties of the input data need to be captured by the codes. Kernel machines have experienced great success by operating via inner-products in a theoretically well-defined reproducing kernel Hilbert space, hence capturing topological properties of input data. In this paper, we enhance the autoencoder's ability to learn effective data representations by aligning inner products between codes with respect to a kernel matrix. By doing so, the proposed kernelized autoencoder allows learning similarity-preserving embeddings of input data, where the notion of similarity is explicitly controlled by the user and encoded in a positive semi-definite kernel matrix. Experiments are performed for evaluating both reconstruction and kernel alignment performance in classification tasks and visualization of high-dimensional data. Additionally, we show that our method is capable to emulate kernel principal component analysis on a denoising task, obtaining competitive results at a much lower computational cost.
Is part of
Løkse, S. (2020). Leveraging Kernels for Unsupervised Learning. (Doctoral thesis). https://hdl.handle.net/10037/19911.
Publisher
Elsevier
Citation
Kampffmeyer, M., Løkse, S., Bianchi, F.M., Jenssen, R. & Livi, L. (2018). The deep kernelized autoencoder. Applied Soft Computing, 71, 816-825. https://doi.org/10.1016/j.asoc.2018.07.029
Metadata
Show full item record
Collections
  • Artikler, rapporter og annet (fysikk og teknologi) [1057]

Browse

Browse all of MuninCommunities & CollectionsAuthor listTitlesBy Issue DateBrowse this CollectionAuthor listTitlesBy Issue Date
Login

Statistics

View Usage Statistics
UiT

Munin is powered by DSpace

UiT The Arctic University of Norway
The University Library
uit.no/ub - munin@ub.uit.no

Accessibility statement (Norwegian only)