Detail publikace

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.

Originální název

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

Typ

různé

Jazyk

angličtina

Originální abstrakt

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.

Klíčová slova

orthogonal projections; dimension reduction; augmented target loss;

Autoři

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

Vydáno

1. 4. 2020

Nakladatel

SPRINGER

Místo

DORDRECHT

Strany od

395

Strany do

395

Strany počet

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"
}