Dynamical systems as temporal feature spaces

Research output: Contribution to journalArticlepeer-review

2 Citations (Scopus)
148 Downloads (Pure)


Parameterized state space models in the form of recurrent networks are often used in machine learning to learn from data streams exhibiting temporal dependencies. To break the black box nature of such models it is important to understand the dynamical features of the input driving time series that are formed in the state space. We propose a framework for rigorous analysis of such state representations in vanishing memory state space models such as echo state networks (ESN). In particular, we consider the state space a temporal feature space and the readout mapping from the state space a kernel machine operating in that feature space. We show that: (1) The usual ESN strategy of randomly generating input-to-state, as well as state coupling leads to shallow memory time series representations, corresponding to cross-correlation operator with fast exponentially decaying coefficients; (2) Imposing symmetry on dynamic coupling yields a constrained dynamic kernel matching the input time series with straightforward exponentially decaying motifs or exponentially decaying motifs of the highest frequency; (3) Simple ring (cycle) highdimensional reservoir topology specified only through two free parameters can implement deep memory dynamic kernels with a rich variety of matching motifs. We quantify richness of feature representations imposed by dynamic kernels and demonstrate that for dynamic kernel associated with cycle reservoir topology, the kernel richness undergoes a phase transition close to the edge of stability.
Original languageEnglish
Article number19-589
Pages (from-to)1-42
Number of pages42
JournalJournal of Machine Learning Research
Issue number44
Publication statusPublished - 20 Feb 2020


  • Recurrent Neural Network
  • Echo State Network
  • Dynamical Systems
  • Time Series
  • Kernel Machines


Dive into the research topics of 'Dynamical systems as temporal feature spaces'. Together they form a unique fingerprint.

Cite this