SOM-CPC: Unsupervised Contrastive Learning with Self-Organizing Maps for Structured Representations of High-Rate Time Series

Continuous monitoring with an ever-increasing number of sensors has become ubiquitous across many application domains. Acquired data are typically high-dimensional and difficult to interpret, but they are also hypothesized to lie on a lower-dimensional manifold. Many deep learning (DL) models aim to identify this manifold, but do not promote structure nor interpretability. We propose the SOM-CPC model, which jointly optimizes Contrastive Predictive Coding (CPC), and a Self-Organizing Map (SOM) to find such an organized manifold. We address a largely unexplored and challenging set of scenarios comprising high-rate time series, and show on synthetic and real-life medical and audio data that SOM-CPC outperforms strong baseline models that combine DL with SOMs. SOM-CPC has great potential to expose latent patterns in high-rate data streams, and may therefore contribute to a better understanding of many different processes and systems.