NanoLEDs for energy-efficient and gigahertz-speed spike-based sub-λ neuromorphic nanophotonic computing

Abstract

<jats:title>Abstract</jats:title><jats:p>Event-activated biological-inspired subwavelength (sub-<jats:italic>λ</jats:italic>) photonic neural networks are of key importance for future energy-efficient and high-bandwidth artificial intelligence systems. However, a miniaturized light-emitting nanosource for spike-based operation of interest for neuromorphic optical computing is still lacking. In this work, we propose and theoretically analyze a novel nanoscale nanophotonic neuron circuit. It is formed by a quantum resonant tunneling (QRT) nanostructure monolithic integrated into a sub-<jats:italic>λ</jats:italic> metal-cavity nanolight-emitting diode (nanoLED). The resulting optical nanosource displays a negative differential conductance which controls the all-or-nothing optical spiking response of the nanoLED. Here we demonstrate efficient activation of the spiking response via high-speed nonlinear electrical modulation of the nanoLED. A model that combines the dynamical equations of the circuit which considers the nonlinear voltage-controlled current characteristic, and rate equations that takes into account the Purcell enhancement of the spontaneous emission, is used to provide a theoretical framework to investigate the optical spiking dynamic properties of the neuromorphic nanoLED. We show inhibitory- and excitatory-like optical spikes at multi-gigahertz speeds can be achieved upon receiving exceptionally low (sub-10 mV) synaptic-like electrical activation signals, lower than biological voltages of 100 mV, and with remarkably low energy consumption, in the range of 10–100 fJ per emitted spike. Importantly, the energy per spike is roughly constant and almost independent of the incoming modulating frequency signal, which is markedly different from conventional current modulation schemes. This method of spike generation in neuromorphic nanoLED devices paves the way for sub-<jats:italic>λ</jats:italic> incoherent neural elements for fast and efficient asynchronous neural computation in photonic spiking neural networks.</jats:p>

Resonant tunnelling diode nano-optoelectronic spiking nodes for neuromorphic information processing

“…This brings the possibility of all-in-one monolithic integration of the required functional blocks into singular sub-micron scale devices. For non-coherent signalling between nodes, the RTD-LD can also be realized using an RTD-LED sub-λ element at high (multi-gigahertz) speeds with very low power consumption (<1 pJ per emitted spike) [36]. It was observed that the light emission efficiency of the pillar design increases with smaller sizes, with sub-lambda pillars yielding very high light-extraction efficiency [37].…”

Ultrafast neuromorphic photonic image processing with a VCSEL neuron

“…Recently, investigations into photonic Artificial Neural Networks (ANNs) and neuromorphic systems have been on the rise. Optical devices, such as quantum resonant tunnelling (QRT) structures 8 – 10 , optical modulators 11 , phase-change materials (PCMs) 12 and semiconductor lasers (SLs) 13 – 17 , to name a few, have all been investigated as candidates for novel neuromorphic photonic processing systems. Yet with the field still in its infancy, some investigations have already flourished into efforts to accelerate information processing in photonics with ANNs 18 – 20 , and reservoir computing systems 21 , 22 .…”

Oscillator Finite-Difference Time-Domain (O-FDTD) electric field propagation model: integrated photonics and networks

“…Planar photonic devices embody countless applications ranging from biosensing [5] to photonic computing [6]. Most dielectric and semiconductor devices rely on coherent effects such as waveguiding, interference, and resonances.…”

“…In the current fast-forward technological age, computation power and efficiency are vital, where photonic computation is the most promising fast and lowpower alternative to conventional computing. In particular, photonic neuromorphic platforms promise hardware-based artificial intelligence implementations such as artificial neural networks [6]. Alongside the spiking neuron device, the on-chip interconnection of complex neuron architectures avoiding channel superposition and crosstalk remains challenging.…”