Optical convolutional neural network with atomic nonlinearity

TL;DR

This paper demonstrates a three-layer optical convolutional neural network utilizing atomic vapor for nonlinearity, achieving nearly 84% accuracy on MNIST, highlighting the potential for low-power, optical neural hardware.

Contribution

It introduces a novel optical CNN architecture with atomic vapor nonlinearity, showing practical implementation and classification performance.

Findings

Achieved 83.96% accuracy on MNIST dataset.

Validated the system's performance through experimental characterization.

Demonstrated the viability of atomic nonlinearities for low-power optical neural networks.

Abstract

Due to their high degree of parallelism, fast processing speeds and low power consumption, analog optical functional elements offer interesting routes for realizing neuro-morphic computer hardware. For instance, convolutional neural networks lend themselves to analog optical implementations by exploiting the Fourier-transform characteristics of suitable designed optical setups. However, the efficient implementation of optical nonlinearities for such neural networks still represents challenges. In this work, we report on the realization and characterization of a three-layer optical convolutional neural network where the linear part is based on a 4f-imaging system and the optical nonlinearity is realized via the absorption profile of a cesium atomic vapor cell. This system classifies the handwritten digital dataset MNIST with 83.96% accuracy, which agrees well with corresponding simulations. Our results thus demonstrate the viability of utilizing atomic nonlinearities in neural network architectures with low power consumption.