Work

Harnessing Phase Dynamics Across Diverse Frequencies with Multifrequency Oscillatory Neural Networks

Year: 2025

Type: article

Abstract: Oscillatory Neural Networks (ONNs) are an emerging computing paradigm that encodes information in the phase difference of coupled oscillators. Traditionally, ONNs have been investigated using homogeneous frequency oscillators. However, physical hardware implementations are inherently subject to frequency mismatches, device variability, and nonuniformities, which are typically perceived as undesirable for circuit performance. This work challenges this assumption by inquiring whether frequency discrepancies and multifrequency oscillators can be harnessed for performing computation. First, the frequency variation threshold that oscillators can withstand to compute is derived. Next, for frequency variations beyond such a threshold, a multifrequency ONN computing approach is introduced and validated in both hardware implementation and software simulations by performing pattern retrieval. The results demonstrate computation with nonuniform frequency oscillators and highlight the feasibility of their physical hardware implementation.

Source: Advanced Intelligent Discovery

DOI: 10.1002/aidi.202500152

Authors: Nil Dinç, Filip Sabo, Aida Todri‐Sanial

Institution: Eindhoven University of Technology

Language: English

Topic: Nonlinear Dynamics and Pattern Formation

Subfield: Computer Networks and Communications

Field: Computer Science

Domain: Physical Sciences

Open Access status: diamond

Funders: European Commission, HORIZON EUROPE Framework Programme, HORIZON EUROPE European Research Council

Awards: Phase Change Materials for Energy Efficient Edge Computing, Thermodynamic-inspired computing with oscillatory neural networks, G4211437464, G8801217452, G969996246