Temporal Information Processing With an Integrated Laser Neuron

Peng, Hsuan-Tung; Angelatos, Gerasimos; Lima, Thomas Ferreira de; Nahmias, Mitchell A.; Tait, Alexander N.; Abbaslou, Siamak; Shastri, Bhavin J.; Prucnal, Paul R.

doi:10.1109/jstqe.2019.2927582

Cited by 51 publications

(18 citation statements)

References 34 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Since then, various biological properties and learning tasks of spiking neurons have been demonstrated experimentally and numerically. Fiber‐based graphene excitable lasers (GELs), [ 8,112,113 ] micropillar lasers with integrated SAs, [ 48,114–116 ] DFBs, [ 117,118 ] and VCSEL‐SAs [ 102,119–122 ] all fall under this category. In addition, it is worth mentioning that a circuit model has been proposed by mapping the rate equations of excitable lasers with an embedded SA to an equivalent circuit; therefore, the signal‐processing behaviors such as excitation and inhibition can be efficiently and accurately simulated with the SPICE engine.…”

Section: Photonic Integrated Neuronsmentioning

confidence: 99%

“…[ 117 ] More recently, an integrated photonic spiking processor directly implementing the analog O/E/O link was demonstrated. [ 49 ] As shown in Figure a, the integrated chip mainly consists of nine two‐section DFB laser neurons, pairs of high‐speed balanced photodetectors (BPDs), together with connecting metal wires. Each DFB laser is composed of a large gain section and a small absorber section, which are optically coupled but electrically isolated.…”

Section: Photonic Integrated Neuronsmentioning

confidence: 99%

“…[ 42 ] Nonlinear activation functions in PNNs have been implemented with creative combinations of classic photonic primitives, including microring resonators (MRRs), [ 43 ] Mach–Zehnder interferometers (MZIs), [ 44 ] semiconductor optical amplifiers (SOAs), [ 45 ] and electro‐optic modulators together with photodetectors. [ 43,46 ] In addition, typical biological features of the spiking neuron have been successfully emulated with different types of excitable lasers, i.e., vertical‐cavity surface‐emitting lasers (VCSELS), [ 47 ] micropillar lasers, [ 48 ] distributed feedback lasers (DFBs), [ 49 ] and quantum‐dot (QDs) lasers. [ 50,51 ] Meanwhile, phase‐change materials (PCMs), which can be flexibly switched between multiple states of different optical properties, [ 52,53 ] have emerged as a competitive alternative in hardware emulation of both the fundamental leaky integrate‐and‐fire (LIF) functionality of neurons and the plastic weighting process of synapses.…”

Section: Introductionmentioning

confidence: 99%

See 2 more Smart Citations

Integrated Neuromorphic Photonics: Synapses, Neurons, and Neural Networks

Guo

Xiang

Zhang

et al. 2021

Advanced Photonics Research

View full text Add to dashboard Cite

Ever‐growing demands of bandwidth, computing speed, and power consumption are now accelerating the transformation of computing research, as work‐at‐home becomes a new normal. Brain‐inspired photonic neuromorphic computing for artificial intelligence is raising an urgent need, and it promises orders‐of‐magnitude higher computing speed and energy efficiency compared with digital electronic counterparts. Photonic neuromorphic networks combine the efficiency of neural networks based on a non‐von Neumann architecture and the benefits of photonics to constitute a new computing paradigm. Herein, some recent advances in photonic neural networks are reviewed, including the concept, principle, key photonic components, and architectures that construct the neuromorphic systems, hoping to provide a better understanding of this emerging field.

show abstract

Section: Photonic Integrated Neuronsmentioning

confidence: 99%

Section: Photonic Integrated Neuronsmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Integrated Neuromorphic Photonics: Synapses, Neurons, and Neural Networks

Guo

Xiang

Zhang

et al. 2021

Advanced Photonics Research

View full text Add to dashboard Cite

show abstract

“…Although these architectures do not use spike-based learning they are capable of remarkable light-based, human-like, recognition tasks under supervised learning [15]. In order reproduce the powerful computation of biological neurons at lower energy cost there has been numerous implementations of spike-based photonic neurons using graphene excitable lasers [17], distributed feedback (DFB) lasers [18], verticalcavity surface-emitting lasers (VCSEL) [19,20], timedelayed optoelectronic nanoscale resonators [21], micropillar lasers [22], or phase change materials [23] to name a few (for an extensive review see [24]). Nevertheless, the large footprint (>100 μm 2 ) of most of these elements is imposing a bottleneck for compact and efficient optical SNNs.…”

Section: Introductionmentioning

confidence: 99%

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

2020

View full text Add to dashboard Cite

AbstractEvent-activated biological-inspired subwavelength (sub-λ) 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-λ 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-λ incoherent neural elements for fast and efficient asynchronous neural computation in photonic spiking neural networks.

show abstract

“…Neuromorphic photonics is a research field that can revolutionize optical signal processing, optical computing and artificial intelligence. [1][2][3][4] Optical neural networks can potentially outperform (by orders of magnitude) electronic neural networks, both, in signal processing speed and in energy consumption. However, to implement such ultrafast photonic neural networks we need to identify low-cost and energy-efficient excitable lasers whose output mimics neuronal activity.…”

Section: Introductionmentioning

confidence: 99%