Rate-Invariant Autoencoding of Time-Series

Kaushik Koneripalli, Suhas Lohit, Rushil Anirudh, Pavan Turaga

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Abstract

For time-series classification and retrieval applications, an important requirement is to develop representations/metrics that are robust to re-parametrization of the time-axis. Temporal re-parametrization as a model can account for variability in the underlying generative process, sampling rate variations, or plain temporal mis-alignment. In this paper, we extend prior work in disentangling latent spaces of autoencoding models, to design a novel architecture to learn rate-invariant latent codes in a completely unsupervised fashion. Unlike conventional neural network architectures, this method allows to explicitly disentangle temporal parameters in the form of order-preserving diffeomorphisms with respect to a learnable template. This makes the latent space more easily interpretable. We show the efficacy of our approach on a synthetic dataset and a real dataset for hand action-recognition.

Original languageEnglish (US)
Title of host publication2020 IEEE International Conference on Acoustics, Speech, and Signal Processing, ICASSP 2020 - Proceedings
PublisherInstitute of Electrical and Electronics Engineers Inc.
Pages3732-3736
Number of pages5
ISBN (Electronic)9781509066315
DOIs
StatePublished - May 2020
Event2020 IEEE International Conference on Acoustics, Speech, and Signal Processing, ICASSP 2020 - Barcelona, Spain
Duration: May 4 2020May 8 2020

Publication series

NameICASSP, IEEE International Conference on Acoustics, Speech and Signal Processing - Proceedings
Volume2020-May
ISSN (Print)1520-6149

Conference

Conference2020 IEEE International Conference on Acoustics, Speech, and Signal Processing, ICASSP 2020
Country/TerritorySpain
CityBarcelona
Period5/4/205/8/20

Keywords

  • Rate-invariance
  • autoencoder
  • deep learning
  • neural networks
  • time-series

ASJC Scopus subject areas

  • Software
  • Signal Processing
  • Electrical and Electronic Engineering

Fingerprint

Dive into the research topics of 'Rate-Invariant Autoencoding of Time-Series'. Together they form a unique fingerprint.

Cite this