Parity-time symmetric optical neural networks

TL;DR

This paper introduces a novel optical neural network architecture using parity-time symmetric couplers, which trains via gain/loss adjustments instead of phase modulation, offering a potentially faster and more efficient approach for optical computing.

Contribution

The paper proposes a PT-symmetric optical neural network architecture that replaces phase shifters with gain/loss contrasts, enabling faster training and comparable accuracy on MNIST.

Findings

Achieves 67% accuracy on MNIST, close to 71% of conventional ONNs.

Circumvents phase modulation issues, enabling potentially faster training.

Demonstrates the feasibility of PT-symmetric components in neural network applications.

Abstract

Optical neural networks (ONNs), implemented on an array of cascaded Mach-Zehnder interferometers (MZIs), have recently been proposed as a possible replacement for conventional deep learning hardware. They potentially offer higher energy efficiency and computational speed when compared to their electronic counterparts. By utilizing tunable phase shifters, one can adjust the output of each of MZIs in order to enable emulation of arbitrary matrix-vector multiplication. These phase shifters are central to the programmability of ONNs, but they require large footprint and are relatively slow. Here we propose an ONN architecture that utilizes parity-time (PT) symmetric couplers as its building blocks. Instead of modulating phase, gain/loss contrasts across the array are adjusted as a means to train the network. We demonstrate that PT symmetric optical neural networks (PT-ONN) are adequately expressive by performing the digit-recognition task on the modified national institute of standard and technology (MNIST) dataset. Compared to conventional ONNs, the PT-ONN achieves a comparable accuracy (67% vs. 71%) while circumventing the problems associated with changing phase. Our approach may lead to new and alternative avenues for fast training in chip-scale optical neural networks.