# TimeCaps: Capturing Time Series Data With Capsule Networks

arXiv: https://arxiv.org/abs/1911.11800 · HTML: https://mlsanity.com/paper/1911.11800/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 26 Nov 2019.

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

- [1D-CapsNet-LSTM: A Deep Learning-Based Model for Multi-Step Stock Index Forecasting](https://mlsanity.com/paper/2310.02090/) (2023)

## Abstract (arXiv)

Capsule networks excel in understanding spatial relationships in 2D data for vision related tasks. Even though they are not designed to capture 1D temporal relationships, with TimeCaps we demonstrate that given the ability, capsule networks excel in understanding temporal relationships. To this end, we generate capsules along the temporal and channel dimensions creating two temporal feature detectors which learn contrasting relationships. TimeCaps surpasses the state-of-the-art results by achieving 96.21% accuracy on identifying 13 Electrocardiogram (ECG) signal beat categories, while achieving on-par results on identifying 30 classes of short audio commands. Further, the instantiation parameters inherently learnt by the capsule networks allow us to completely parameterize 1D signals which opens various possibilities in signal processing.