Photonic spiking neural networks and CMOS-compatible graphene-on-silicon spiking neurons

Abstract

Spiking neural networks are known to be superior over artificial neural networks for their computational power efficiency and noise robustness. The benefits of spiking coupled with the high-bandwidth and low-latency of photonics can enable highly-efficient, noise-robust, high-speed neural processors. The landscape of photonic spiking neurons consists of an overwhelming majority of excitable lasers and a few demonstrations on nonlinear optical cavities. The silicon platform is best poised to host a scalable photonic technology given its CMOS-compatibility and low optical loss. Here, we present a survey of existing photonic spiking neurons, and propose a novel spiking neuron based on a hybrid graphene-on-silicon microring cavity. A comparison among a representative sample of photonic spiking devices is also presented. Finally, we discuss methods employed in training spiking neural networks, their challenges as well as the application domain that can be enabled by photonic spiking neural hardware.

References in corpus (5)

• Photonics for artificial intelligence and neuromorphic computing
• Graphene-Based Integrated Photonics For Next-Generation Datacom And Telecom
• Measuring the Nonlinear Refractive Index of Graphene using the Optical Kerr Effect Method
• Negative Kerr nonlinearity of graphene as seen via chirped-pulse-pumped self-phase modulation
• Temporal Pulses Driven Spiking Neural Network for Fast Object Recognition in Autonomous Driving

Cited by in corpus (3)

• Photonic neural networks based on integrated silicon microresonators
• Deep Photonic Reservoir Computer Based on Frequency Multiplexing with Fully Analog Connection Between Layers
• Interfacing spiking VCSEL-neurons with silicon photonics weight banks towards integrated neuromorphic photonic systems