# Approximating DTW with a convolutional neural network on EEG data

arXiv: https://arxiv.org/abs/2301.12873 · HTML: https://mlsanity.com/paper/2301.12873/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 12 of its 23 references that are in the map.
- First posted on arXiv 30 Jan 2023.

## Builds on (most cited first, 12 of 12)

- [An Empirical Evaluation of Generic Convolutional and Recurrent Networks for Sequence Modeling](https://mlsanity.com/paper/1803.01271/) (2018)
- [Soft-DTW: a Differentiable Loss Function for Time-Series](https://mlsanity.com/paper/1703.01541/) (2017)
- [XSleepNet: Multi-View Sequential Model for Automatic Sleep Staging](https://mlsanity.com/paper/2007.05492/) (2020)
- [SleepEEGNet: Automated Sleep Stage Scoring with Sequence to Sequence Deep Learning Approach](https://mlsanity.com/paper/1903.02108/) (2019)
- [Joint Classification and Prediction CNN Framework for Automatic Sleep Stage Classification](https://mlsanity.com/paper/1805.06546/) (2018)
- [Learning Wasserstein Embeddings](https://mlsanity.com/paper/1710.07457/) (2017)
- [Learning Discriminative Prototypes with Dynamic Time Warping](https://mlsanity.com/paper/2103.09458/) (2021)
- [Multivariate Time Series Classification Using Dynamic Time Warping Template Selection for Human Activity Recognition](https://mlsanity.com/paper/1512.06747/) (2015)
- [Automatic Sleep Stage Scoring with Single-Channel EEG Using Convolutional Neural Networks](https://mlsanity.com/paper/1610.01683/) (2016)
- [Automatic sleep stage classification with deep residual networks in a mixed-cohort setting](https://mlsanity.com/paper/2008.09416/) (2020)
- [Time series classification for varying length series](https://mlsanity.com/paper/1910.04341/) (2019)
- [Dynamic Time Warping as a New Evaluation for Dst Forecast with Machine Learning](https://mlsanity.com/paper/2006.04667/) (2020)

## Built on by (most cited first, 1 of 1)

- [ViRAC: A Vision-Reasoning Agent Head Movement Control Framework in Arbitrary Virtual Environments](https://mlsanity.com/paper/2502.10046/) (2025)

## Abstract (arXiv)

Dynamic Time Wrapping (DTW) is a widely used algorithm for measuring similarities between two time series. It is especially valuable in a wide variety of applications, such as clustering, anomaly detection, classification, or video segmentation, where the time-series have different timescales, are irregularly sampled, or are shifted. However, it is not prone to be considered as a loss function in an end-to-end learning framework because of its non-differentiability and its quadratic temporal complexity. While differentiable variants of DTW have been introduced by the community, they still present some drawbacks: computing the distance is still expensive and this similarity tends to blur some differences in the time-series. In this paper, we propose a fast and differentiable approximation of DTW by comparing two architectures: the first one for learning an embedding in which the Euclidean distance mimics the DTW, and the second one for directly predicting the DTW output using regression. We build the former by training a siamese neural network to regress the DTW value between two time-series. Depending on the nature of the activation function, this approximation naturally supports differentiation, and it is efficient to compute. We show, in a time-series retrieval context on EEG datasets, that our methods achieve at least the same level of accuracy as other DTW main approximations with higher computational efficiency. We also show that it can be used to learn in an end-to-end setting on long time series by proposing generative models of EEGs.