Interfacing spiking VCSEL-neurons with silicon photonics weight banks towards integrated neuromorphic photonic systems

TL;DR

This paper demonstrates the integration of ultrafast spiking VCSEL-neurons with silicon photonic weight banks, enabling optical amplitude weighting and rate-coding functionalities crucial for neuromorphic photonic systems.

Contribution

It experimentally shows how VCSEL-neurons can be combined with silicon photonic micro-ring resonators for neuromorphic computing applications.

Findings

MRR weightbanks perform amplitude weighting of sub-ns optical spikes

VCSEL-neurons can be directly modulated via micro-ring resonators

Optical spike rate-coding achieved through thermal tuning of micro-ring

Abstract

Spiking neurons and neural networks constitute a fundamental building block for brain-inspired computing, which is posed to benefit significantly from photonic hardware implementations. In this work, we experimentally investigate an interconnected system based on an ultrafast spiking VCSEL-neuron and a silicon photonics (SiPh) integrated micro-ring resonator (MRR) weight bank, and demonstrate two different functional arrangements of these devices. First, we show that MRR weightbanks can be used in conjuction with the spiking VCSEL-neurons to perform amplitude weighting of sub-ns optical spiking signals. Second, we show that a continuous firing VCSEL-neuron can be directly modulated using a locking signal propagated through a single weighting micro-ring, and we utilize this functionality to perform optical spike firing rate-coding via thermal tuning of the micro-ring resonator. Given the significant track record of both integrated weight banks and photonic VCSEL-neurons, we believe these results demonstrate the viability of combining these two classes of devices for use in functional neuromorphic photonic systems.