Tensor-based algorithms for image classification

Stefan Klus*, Patrick Gelß

*Corresponding author for this work

Research output: Contribution to journalArticlepeer-review

17 Citations (Scopus)
56 Downloads (Pure)

Abstract

Interest in machine learning with tensor networks has been growing rapidly in recent years. We show that tensor-based methods developed for learning the governing equations of dynamical systems from data can, in the same way, be used for supervised learning problems and propose two novel approaches for image classification. One is a kernel-based reformulation of the previously introduced multidimensional approximation of nonlinear dynamics (MANDy), the other an alternating ridge regression in the tensor train format. We apply both methods to the MNIST and fashion MNIST data set and show that the approaches are competitive with state-of-the-art neural network-based classifiers.

Original languageEnglish
Article number240
JournalAlgorithms
Volume12
Issue number11
DOIs
Publication statusPublished - Nov 2019

Keywords

  • Image classification
  • Kernel-based methods
  • Quantum machine learning
  • Ridge regression
  • Tensor train format

ASJC Scopus subject areas

  • Theoretical Computer Science
  • Numerical Analysis
  • Computational Theory and Mathematics
  • Computational Mathematics

Fingerprint

Dive into the research topics of 'Tensor-based algorithms for image classification'. Together they form a unique fingerprint.

Cite this