High speed and reconfigurable optronic neural network with digital nonlinear activation

TL;DR

This paper presents a high-speed, reconfigurable optical neural network using a 4f system and digital nonlinear activation, achieving 93.66% accuracy on MNIST and surpassing existing free-space optical neural networks in spatial complexity.

Contribution

It introduces a programmable, high-speed optical neural network with digital nonlinear activation, improving spatial complexity over previous free-space optical neural networks.

Findings

Achieved 93.66% recognition accuracy on MNIST.

Demonstrated reconfigurability and high speed of the optical neural network.

Outperformed existing free-space optical neural networks in spatial complexity.

Abstract

With its unique parallel processing capability, optical neural network has shown low-power consumption in image recognition and speech processing. At present, the manufacturing technology of programmable photonic chip is not mature, and the realization of optical neural network in free-space is still a hot spot of intelligent optical computing. In this article, based on MNIST datasets and 4f system, three-layer optical neural networks are constructed, whose recognition accuracy can reach 93.66%. Our network is programmable, high speed, reconfigurable and is better than the existing free-space optical neural network in terms of spatial complexity.