Publication detail

On Orthogonal Projections for Dimension Reduction and Applications in Augmented Target Loss Functions for Learning Problems (vol 31, pg 245, 2020)

BREGER, A. ORLANDO, J. HARÁR, P. DÖRFLER, M. KLIMSCHA, S. GRECHENIG, C. GERENDAS, B. SCHMIDT-ERFURTH, U. EHLER, M.

Original Title

On Orthogonal Projections for Dimension Reduction and Applications in Augmented Target Loss Functions for Learning Problems (vol 31, pg 245, 2020)

Type

miscellaneous

Language

English

Original Abstract

The use of orthogonal projections on high-dimensional input and target data in learning frameworks is studied. First, we investigate the relations between two standard objectives in dimension reduction, preservation of variance and of pairwise relative distances. Investigations of their asymptotic correlation as well as numerical experiments show that a projection does usually not satisfy both objectives at once. In a standard classification problem we determine projections on the input data that balance the objectives and compare subsequent results. Next, we extend our application of orthogonal projections to deep learning tasks and introduce a general framework of augmented target loss functions. These loss functions integrate additional information via transformations and projections of the target data. In two supervised learning problems, clinical image segmentation and music information classification, the application of our proposed augmented target loss functions increase the accuracy.

Keywords

orthogonal projections; dimension reduction; augmented target loss;

Authors

BREGER, A.; ORLANDO, J.; HARÁR, P.; DÖRFLER, M.; KLIMSCHA, S.; GRECHENIG, C.; GERENDAS, B.; SCHMIDT-ERFURTH, U.; EHLER, M.

Released

1. 4. 2020

Publisher

SPRINGER

Location

DORDRECHT

Pages from

395

Pages to

395

Pages count

1

URL

https://link.springer.com/content/pdf/10.1007/s10851-019-00927-7.pdf

BibTex

@misc{BUT177193,
  author="Anna {Breger} and Jose Ignacio {Orlando} and Pavol {Harár} and Monika {Dörfler} and Sophie {Klimscha} and Christoph {Grechenig} and Bianca {Gerendas} and Ursula {Schmidt-Erfurth} and Martin {Ehler}",
  title="On Orthogonal Projections for Dimension Reduction and Applications in Augmented Target Loss Functions for Learning Problems (vol 31, pg 245, 2020)",
  year="2020",
  pages="395--395",
  publisher="SPRINGER",
  address="DORDRECHT",
  doi="10.1007/s10851-019-00927-7",
  url="https://link.springer.com/content/pdf/10.1007/s10851-019-00927-7.pdf",
  note="miscellaneous"
}