Compact and Low-Loss PCM-based Silicon Photonic MZIs for Photonic Neural Networks

TL;DR

This paper introduces a compact, low-loss Mach-Zehnder Interferometer using phase change materials, enhancing scalability and accuracy in photonic neural networks by reducing loss and crosstalk.

Contribution

It presents an optimized MZI design with minimal loss and crosstalk, advancing the integration of photonic neural networks.

Findings

0.2 dB insertion loss achieved

-38 dB crosstalk level

52 micrometer device length

Abstract

We present an optimized Mach-Zehnder Interferometer (MZI) with phase change materials for photonic neural networks (PNNs). With 0.2 dB loss, -38 dB crosstalk, and length of 52 micrometer, the designed MZI significantly improves the scalability and accuracy of PNNs under loss and crosstalk.