Transparent conductive oxides and low loss nitride-rich silicon waveguides as building blocks for neuromorphic photonics

TL;DR

This paper proposes a CMOS-compatible photonic platform combining nitride-rich silicon waveguides and transparent conductive oxides to enable ultrafast, low-energy neuromorphic photonic memory devices for artificial neural networks.

Contribution

It introduces a novel photonic platform integrating low-loss silicon guides with conductive oxides for high nonlinearity and bistability, advancing neuromorphic photonics.

Findings

Potential for ultrafast, low-energy neural network hardware

Integration of low-loss materials for improved performance

Enabling bistability with electrical and optical signals

Abstract

Fully CMOS-compatible photonic memory holding devices hold a potential in a development of ultrafast artificial neural networks. Leveraging the benefits of photonics such as high-bandwidth, low latencies, low-energy interconnect and high speed they can overcome the existing limits of the electronic processing. To satisfy all these requirements a new photonic platform is proposed that combines low-loss nitride-rich silicon as a guide and low-loss transparent conductive oxides as an active material that can provide high nonlinearity and bistability under both electrical and optical signals.