Digitized Phase Change Material Heterostack for Diffractive Optical Neural Network

TL;DR

This paper introduces a digitized heterostack architecture with multiple phase change material layers for diffractive optical neural networks, enhancing reconfigurability and performance for energy-efficient machine learning hardware.

Contribution

It presents a novel multilayer PCM heterostack design that improves multilevel operation capabilities and system performance in diffractive optical neural networks.

Findings

Electrical tuning of PCM layers demonstrated

Thermal analysis informs device design to prevent crosstalk

Heterostacks achieve large phase modulation range

Abstract

All-optical and fully reconfigurable diffractive optical neural network (DONN) architectures are promising for high-throughput and energy-efficient machine learning (ML) hardware accelerators for broad applications. However, current device and system implementations have limited performance. This work demonstrates a novel diffractive device architecture, which is named digitized heterostack and consists of multiple layers of nonvolatile phase change materials (PCMs) with different thicknesses. This architecture can both leverage the advantages of PCM optical properties and mitigate challenges associated with implementing multilevel operations in a single PCM layer. Proof-of-concept experiments demonstrate the electrical tuning of one PCM layer in a spatial light modulation device, and thermal analysis guides the design of DONN devices and systems to avoid thermal crosstalk if individual heterostacks are assembled into an array. Further, heterostacks containing three PCM layers are designed to have a large phase modulation range and uniform coverage and the ML performance of DONN systems with designed heterostacks is evaluated. The developed device architecture provides new opportunities for desirable energy-efficient, fast-reconfigured, and compact DONN systems in the future.