Autoencoding Time Series for Visualisation
This work addresses visualization challenges for time series data, but it appears incremental as it combines existing techniques like echo state networks and autoencoders without introducing a fundamentally new approach.
The authors tackled the problem of visualizing time series by developing an algorithm that uses echo state networks and autoencoders to capture latent dynamics and create visualizations from bottleneck activations, demonstrating it on synthetic and real data.
We present an algorithm for the visualisation of time series. To that end we employ echo state networks to convert time series into a suitable vector representation which is capable of capturing the latent dynamics of the time series. Subsequently, the obtained vector representations are put through an autoencoder and the visualisation is constructed using the activations of the bottleneck. The crux of the work lies with defining an objective function that quantifies the reconstruction error of these representations in a principled manner. We demonstrate the method on synthetic and real data.