Research

Learning Alignments from Latent Space Structures


Reference:

Kazlauskaite, I., Ek, C. H. and Campbell, N., 2016. Learning Alignments from Latent Space Structures. In: NIPS Workshop on Learning in High Dimensions with Structure, 2016-12-09.

Related documents:

[img]
Preview
PDF (lhds16_alignments) - Requires a PDF viewer such as GSview, Xpdf or Adobe Acrobat Reader
Download (1462kB) | Preview

    Abstract

    In this paper we present a model that is capable of learning alignments between high-dimensional data by exploiting low-dimensional structures. Specifically, our method uses a Gaussian process latent variable model (GP-LVM) to learn alignments and latent representations simultaneously. The results show that our model performs alignment implicitly and improves the smoothness of the low dimensional representations.

    Details

    Item Type Conference or Workshop Items (Paper)
    CreatorsKazlauskaite, I., Ek, C. H. and Campbell, N.
    DepartmentsFaculty of Science > Computer Science
    Research CentresEPSRC Centre for Doctoral Training in Statistical Mathematics (SAMBa)
    RefereedYes
    StatusPublished
    ID Code54607

    Export

    Actions (login required)

    View Item

    Document Downloads

    More statistics for this item...