Research Area:  Machine Learning

Abstract:

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.

Keywords:  

Author(s) Name:   Hirunima Jayasekara, Vinoj Jayasundara, Jathushan Rajasegaran, Sandaru Jayasekara, Suranga Seneviratne, Ranga Rodrigo

Publisher name:  arXiv:1911.11800

DOI:  10.48550/arXiv.1911.11800

Volume Information:  

Paper Link:   https://arxiv.org/abs/1911.11800