Study of Memristor-based Oscillatory Neural Networks using PPV modeling

TL;DR

This paper introduces an efficient PPV modeling method for memristor-based oscillatory neural networks, significantly reducing simulation time and analyzing the effects of circuit parameters on pattern recognition accuracy and robustness.

Contribution

It presents a novel PPV abstraction technique that accelerates large-scale ONN simulations by over 2000 times and explores parameter impacts on performance.

Findings

PPV modeling reduces simulation complexity and time.

Circuit parameters influence pattern recognition accuracy.

The network shows robustness against frequency mismatch.

Abstract

Memristor-based oscillator is becoming promising thanks to its inherent NDR (Negative Differential Region) property and compact circuit structure. This paves the way to the large scale oscillatory neural network (ONN) and the realization of pattern recognition based on its global synchronization. However, the simulation of large scale ONN encounters the problem of long simulation time because of the large number of oscillators. Here we propose a highly efficient method to abstract the phase sensitivity characteristic of the memristor-based oscillator, i.e., its PPV (Perturbation Projection Vector), which allows reducing considerably the complexity of ONN simulation, and speeding up the simulation more than 2000 times. Our study also reveals the impact of the circuit parameters on the pattern recognition accuracy and the robustness against the frequency mismatch.