Coupled VO2 oscillators circuit as analog first layer filter in convolutional neural networks

TL;DR

This paper introduces a novel in-memory computing platform using coupled VO2 oscillators as analog filters in CNNs, demonstrating improved density, frequency, and neuromorphic capabilities for image recognition tasks.

Contribution

The work presents a silicon-based VO2 oscillator crossbar platform and demonstrates its application as an analog filter in CNNs, replacing digital filtering with oscillating circuits.

Findings

Achieved 95% accuracy on MNIST with VGG13 using oscillator-based filtering.

Demonstrated low variability and high reliability of VO2 oscillator devices.

Showed improved area density and oscillation frequency over existing platforms.

Abstract

In this work we present an in-memory computing platform based on coupled VO2 oscillators fabricated in a crossbar configuration on silicon. Compared to existing platforms, the crossbar configuration promises significant improvements in terms of area density and oscillation frequency. Further, the crossbar devices exhibit low variability and extended reliability, hence, enabling experiments on 4-coupled oscillator. We demonstrate the neuromorphic computing capabilities using the phase relation of the oscillators. As a application, we propose to replace digital filtering operation in a convolutional neural network with oscillating circuits. The concept is tested with a VGG13 architecture on the MNIST dataset, achieving performances of 95% in the recognition task.