Skip to Main content Skip to Navigation
Journal articles

How Frequency Injection Locking Can Train Oscillatory Neural Networks to Compute in Phase

Abstract : Brain-inspired computing employs devices and architectures that emulate biological functions for more adaptive and energy efficient systems. Oscillatory neural networks are an alternative approach to mimicking the human brain and suitable for solving large and complex associative problems. In this work, we investigate the dynamics of coupled oscillators to implement such oscillatory neural networks. By harnessing the complex dynamics of coupled oscillatory systems, we forge a novel computation model - that is, information is encoded in the phase of oscillations. Coupled interconnected oscillators can exhibit various behaviors due to the strength of the coupling. Here we present a novel method on how to control the oscillatory states of coupled oscillators that allows them to lock in frequency with distinct phase differences. Circuit-level simulation results indicate the effectiveness of the method and its applicability to large-scale oscillatory networks for pattern recognition.
Complete list of metadata

https://hal-lirmm.ccsd.cnrs.fr/lirmm-03164135
Contributor : Eirini Karachristou <>
Submitted on : Tuesday, March 9, 2021 - 4:41:26 PM
Last modification on : Wednesday, September 15, 2021 - 12:12:03 PM

Identifiers

  • HAL Id : lirmm-03164135, version 1

Citation

Aida Todri-Sanial, Stefania Carapezzi, Corentin Delacour, Madeleine Abernot, Thierry Gil, et al.. How Frequency Injection Locking Can Train Oscillatory Neural Networks to Compute in Phase. IEEE Transactions on Neural Networks and Learning Systems, IEEE, 2021. ⟨lirmm-03164135⟩

Share

Metrics

Record views

207