Training a neural network with exciton-polariton optical nonlinearity

TL;DR

This paper demonstrates a hardware neural network using exciton-polariton nodes with nonlinear activation, enabling efficient backpropagation training and achieving high accuracy on the MNIST benchmark.

Contribution

The authors experimentally realize an optical neural network with exciton-polariton nonlinear nodes that allows for efficient training via backpropagation.

Findings

Achieved high classification accuracy on MNIST.

Demonstrated effective training of an optical neural network.

Showed potential for fast, energy-efficient hardware implementations.

Abstract

In contrast to software simulations of neural networks, hardware implementations have often limited or no tunability. While such networks promise great improvements in terms of speed and energy efficiency, their performance is limited by the difficulty to apply efficient training. We propose and realize experimentally an optical system where highly efficient backpropagation training can be applied through an array of highly nonlinear, non-tunable nodes. The system includes exciton-polariton nodes realizing nonlinear activation functions. We demonstrate a high classification accuracy in the MNIST handwritten digit benchmark in a single hidden layer system.