Weight Sharing and Deep Learning for Spectral Data

Jacob Sogaard Larsen, Line Clemmensen

Research output: Chapter in Book/Report/Conference proceedingArticle in proceedingsResearchpeer-review

Abstract

We propose a novel method to co-train deep convolutional neural networks for data sets of differing position specific data. This is an advantage in chemometrics where individual measurements represent exact chemical compounds, e.g. for given wavelengths, and thus signals cannot be translated or resized without disturbing their interpretation. Our approach outperforms transfer learning for three small data sets co-trained with a medium sized data set.

Original languageEnglish
Title of host publicationProceedings of 2020 IEEE International Conference on Acoustics, Speech, and Signal Processing
PublisherIEEE
Publication dateMay 2020
Pages4227-4231
Article number9053918
ISBN (Electronic)9781509066315
DOIs
Publication statusPublished - May 2020
Event2020 IEEE International Conference on Acoustics, Speech, and Signal Processing, ICASSP 2020 - Barcelona, Spain
Duration: 4 May 20208 May 2020

Conference

Conference2020 IEEE International Conference on Acoustics, Speech, and Signal Processing, ICASSP 2020
CountrySpain
CityBarcelona
Period04/05/202008/05/2020
SponsorIEEE
SeriesICASSP, IEEE International Conference on Acoustics, Speech and Signal Processing - Proceedings
Volume2020-May
ISSN1520-6149

Keywords

  • Co-training
  • Deep Learning
  • Spectroscopic data
  • Transfer Learning
  • Weight Sharing

Fingerprint Dive into the research topics of 'Weight Sharing and Deep Learning for Spectral Data'. Together they form a unique fingerprint.

Cite this