Hardware Realization of Neuromorphic Computing with a 4-Port Photonic Reservoir for Modulation Format Identification

TL;DR

This paper presents a silicon photonic reservoir computing device that efficiently identifies modulation formats in optical communications with near-perfect accuracy, demonstrating robustness and surpassing simulation predictions.

Contribution

It introduces a novel 4-port photonic reservoir computer on silicon-on-insulator for modulation identification, combining experimental validation with high accuracy and robustness.

Findings

Achieves nearly 100% accuracy in modulation format identification.

Demonstrates robustness against fabrication imperfections and delay variations.

Outperforms numerical simulations due to enhanced signal interference.

Abstract

The fields of machine learning and artificial intelligence drive researchers to explore energy-efficient, brain-inspired new hardware. Reservoir computing encompasses recurrent neural networks for sequential data processing and matches the performance of other recurrent networks with less training and lower costs. However, traditional software-based neural networks suffer from high energy consumption due to computational demands and massive data transfer needs. Photonic reservoir computing overcomes this challenge with energy-efficient neuromorphic photonic integrated circuits or NeuroPICs. Here, we introduce a reservoir NeuroPIC used for modulation format identification in C-band telecommunication network monitoring. It is built on a silicon-on-insulator platform with a 4-port reservoir architecture consisting of a set of physical nodes connected via delay lines. We comprehensively describe the NeuroPIC design and fabrication, experimentally demonstrate its performance, and compare it with simulations. The NeuroPIC incorporates non-linearity through a simple digital readout and achieves close to 100% accuracy in identifying several configurations of quadrature amplitude modulation formats transmitted over 20 km of optical fiber at 32 GBaud symbol rate. The NeuroPIC performance is robust against fabrication imperfections like waveguide propagation loss, phase randomization, etc. and delay line length variations. Furthermore, the experimental results exceeded numerical simulations, which we attribute to enhanced signal interference in the experimental NeuroPIC output. Our energy-efficient photonic approach has the potential for high-speed temporal data processing in a variety of applications.