Neuromorphic photonics with electro-absorption modulators

TL;DR

This paper explores the use of electro-absorption modulators to implement nonlinear activation functions in photonic neural networks, analyzing their performance and impact on neural network inference.

Contribution

It models and compares five types of electro-absorption modulators, demonstrating their potential for efficient nonlinear activation in neuromorphic photonics.

Findings

Electro-absorption modulators can effectively implement nonlinear activation functions.

Performance varies with device parameters, affecting neural network accuracy.

Simulation shows promising inference capabilities with optimized modulators.

Abstract

Photonic neural networks benefit from both the high channel capacity- and the wave nature of light acting as an effective weighting mechanism through linear optics. The neuron's activation function, however, requires nonlinearity which can be achieved either through nonlinear optics or electro-optics. Nonlinear optics, while potentially faster, is challenging at low optical power. With electro-optics, a photodiode integrating the weighted products of a photonic perceptron can be paired directly to a modulator, which creates a nonlinear transfer function for efficient operating. Here we model the activation functions of five types of electro-absorption modulators, analyze their individual performance over varying performance parameters, and simulate their combined effect on the inference of the neural network