Pattern Recognition in a Ring of Delayed Phase Oscillators
Jan Philipp Pade, Serhiy Yanchuk, Liang Zhao

TL;DR
This paper demonstrates that a ring of delay-coupled phase oscillators can function as a pattern recognition system by encoding patterns as stable periodic orbits, supported by theoretical analysis and practical recognition results.
Contribution
It introduces a novel oscillator-based pattern recognition model with detailed dynamical analysis and successful application to artificial and speech pattern recognition.
Findings
Multiple stable periodic solutions identified
System stability proven through bifurcation analysis
Successful recognition of artificial and speech patterns
Abstract
We show that a ring of phase oscillators coupled with transmission delays can be used as a pattern recognition system. The introduced model encodes patterns as stable periodic orbits. We present a detailed analysis of the underlying dynamics. In particular, we show that the system possesses a multitude of periodic solutions, prove stability results and present a bifurcation analysis. Furthermore, we show successful recognition results using artificial patterns and speech recordings.
Peer Reviews
No public reviews on file for this paper yet. If you reviewed it on a platform where reviews are public (OpenReview, ICLR, NeurIPS, ICML), you can paste yours below so the community can read it here.
Videos
No videos yet. Explain this paper in a talk, walkthrough, or lecture? Add one.
Taxonomy
TopicsNonlinear Dynamics and Pattern Formation · Neural dynamics and brain function · Chaos control and synchronization
