# Bridging Neural Networks and Dynamic Time Warping for Adaptive Time Series Classification

arXiv: https://arxiv.org/abs/2507.09826 · HTML: https://mlsanity.com/paper/2507.09826/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 15 of its 35 references that are in the map.
- First posted on arXiv 13 Jul 2025.

## Builds on (most cited first, 15 of 15)

- [Prototypical Networks for Few-shot Learning](https://mlsanity.com/paper/1703.05175/) (2017)
- [Inception-v4, Inception-ResNet and the Impact of Residual Connections on Learning](https://mlsanity.com/paper/1602.07261/) (2016)
- [InceptionTime: Finding AlexNet for Time Series Classification](https://mlsanity.com/paper/1909.04939/) (2019)
- [ROCKET: Exceptionally fast and accurate time series classification using random convolutional kernels](https://mlsanity.com/paper/1910.13051/) (2019)
- [Deep Learning: A Critical Appraisal](https://mlsanity.com/paper/1801.00631/) (2018)
- [Benchmarking Multivariate Time Series Classification Algorithms](https://mlsanity.com/paper/2007.13156/) (2020)
- [Fairness in Large Language Models: A Taxonomic Survey](https://mlsanity.com/paper/2404.01349/) (2024)
- [Augmenting Neural Networks with First-order Logic](https://mlsanity.com/paper/1906.06298/) (2019)
- [SalientSleepNet: Multimodal Salient Wave Detection Network for Sleep Staging](https://mlsanity.com/paper/2105.13864/) (2021)
- [Inherently Interpretable Time Series Classification via Multiple Instance Learning](https://mlsanity.com/paper/2311.10049/) (2023)
- [How Case Based Reasoning Explained Neural Networks: An XAI Survey of Post-Hoc Explanation-by-Example in ANN-CBR Twins](https://mlsanity.com/paper/1905.07186/) (2019)
- [Deep interpretable ensembles](https://mlsanity.com/paper/2205.12729/) (2022)
- [Prototype-Anchored Learning for Learning with Imperfect Annotations](https://mlsanity.com/paper/2206.11602/) (2022)
- [Learning Interpretable Shapelets for Time Series Classification through Adversarial Regularization](https://mlsanity.com/paper/1906.00917/) (2019)
- [Time Series Data Augmentation as an Imbalanced Learning Problem](https://mlsanity.com/paper/2404.18537/) (2024)

## Abstract (arXiv)

Neural networks have achieved remarkable success in time series classification, but their reliance on large amounts of labeled data for training limits their applicability in cold-start scenarios. Moreover, they lack interpretability, reducing transparency in decision-making. In contrast, dynamic time warping (DTW) combined with a nearest neighbor classifier is widely used for its effectiveness in limited-data settings and its inherent interpretability. However, as a non-parametric method, it is not trainable and cannot leverage large amounts of labeled data, making it less effective than neural networks in rich-resource scenarios. In this work, we aim to develop a versatile model that adapts to cold-start conditions and becomes trainable with labeled data, while maintaining interpretability. We propose a dynamic length-shortening algorithm that transforms time series into prototypes while preserving key structural patterns, thereby enabling the reformulation of the DTW recurrence relation into an equivalent recurrent neural network. Based on this, we construct a trainable model that mimics DTW's alignment behavior. As a neural network, it becomes trainable when sufficient labeled data is available, while still retaining DTW's inherent interpretability. We apply the model to several benchmark time series classification tasks and observe that it significantly outperforms previous approaches in low-resource settings and remains competitive in rich-resource settings.