• Computer Science, Mathematics
  • Published in ArXiv 2019

Dynamic Time Warp Convolutional Networks

@article{Shulman2019DynamicTW,
  title={Dynamic Time Warp Convolutional Networks},
  author={Yaniv Shulman},
  journal={ArXiv},
  year={2019},
  volume={abs/1911.01944}
}
Where dealing with temporal sequences it is fair to assume that the same kind of deformations that motivated the development of the Dynamic Time Warp algorithm could be relevant also in the calculation of the dot product ("convolution") in a 1-D convolution layer. In this work a method is proposed for aligning the convolution filter and the input where they are locally out of phase utilising an algorithm similar to the Dynamic Time Warp. The proposed method enables embedding a non-parametric… CONTINUE READING

References

Publications referenced by this paper.
SHOWING 1-10 OF 22 REFERENCES

Optimizing dynamic time warping’s window width for time series data mining applications

VIEW 3 EXCERPTS
HIGHLY INFLUENTIAL

Dataset: Time series indexing (tsi), Jan 2017

  • C. Wei Tan
  • 2017

Deep Learning for Time-Series Analysis

VIEW 1 EXCERPT

Time series classification from scratch with deep neural networks: A strong baseline

VIEW 2 EXCERPTS