Fischer/etal/2019a: Parameter Sharing for Spatio-Temporal Process Models

Bibtype Inproceedings
Bibkey Fischer/etal/2019a
Author Fischer, Raphael and Piatkowski, Nico and Morik, Katharina
Ls8autor Fischer, Raphael
Morik, Katharina
Piatkowski, Nico
Editor Jäschke, Robert and Weidlich, Matthias
Title Parameter Sharing for Spatio-Temporal Process Models
Booktitle Proceedings of the Conference on "Lernen, Wissen, Daten, Analysen" ({LWDA})
Series {CEUR} Workshop Proceedings
Volume 2454
Pages 89--93
Abstract While probabilistic models such as Markov random fields can be highly beneficial for spatio-temporal data, they often suffer from over-fitting and have limited use in memory-constrained systems. We present a novel method to compress trained models based on temporal parameter sharing, which reduces redundancies in the parameters.
Month 09
Year 2019
Projekt ML2R
Url http://ceur-ws.org/Vol-2454/paper_61.pdf

  • Privacy Policy
  • Imprint