Continuous CNN for nonuniform time series

Hui Shi, Yang Zhang, Hao Wu, Shiyu Chang, Kaizhi Qian, Mark Hasegawa-Johnson, Jishen Zhao

Research output: Contribution to journalConference articlepeer-review


CNN for time series data implicitly assumes that the data are uniformly sampled, whereas many event-based and multimodal data are nonuniform or have heterogeneous sampling rates. Directly applying regular CNN to nonuniform time series is ungrounded, because it is unable to recognize and extract common patterns from the nonuniform input signals. In this paper, we propose the Continuous CNN (CCNN), which estimates the inherent continuous inputs by interpolation, and performs continuous convolution on the continuous input. The interpolation and convolution kernels are learned in an end-toend manner, and are able to learn useful patterns despite the nonuniform sampling rate. Results of several experiments verify that CCNN achieves a better performance on nonuniform data, and learns meaningful continuous kernels.

Original languageEnglish (US)
Pages (from-to)3550-3554
Number of pages5
JournalICASSP, IEEE International Conference on Acoustics, Speech and Signal Processing - Proceedings
StatePublished - 2021
Event2021 IEEE International Conference on Acoustics, Speech, and Signal Processing, ICASSP 2021 - Virtual, Toronto, Canada
Duration: Jun 6 2021Jun 11 2021


  • Convolutional neural network
  • Deep learning
  • Signal processing
  • Time series

ASJC Scopus subject areas

  • Software
  • Signal Processing
  • Electrical and Electronic Engineering


Dive into the research topics of 'Continuous CNN for nonuniform time series'. Together they form a unique fingerprint.

Cite this