Photonics for artificial intelligence and neuromorphic computing

Abstract

Research in photonic computing has flourished due to the proliferation of optoelectronic components on photonic integration platforms. Photonic integrated circuits have enabled ultrafast artificial neural networks, providing a framework for a new class of information processing machines. Algorithms running on such hardware have the potential to address the growing demand for machine learning and artificial intelligence, in areas such as medical diagnosis, telecommunications, and high-performance and scientific computing. In parallel, the development of neuromorphic electronics has highlighted challenges in that domain, in particular, related to processor latency. Neuromorphic photonics offers sub-nanosecond latencies, providing a complementary opportunity to extend the domain of artificial intelligence. Here, we review recent advances in integrated photonic neuromorphic systems, discuss current and future challenges, and outline the advances in science and technology needed to meet those challenges.

21 pages, 6 figures

References in corpus (37)

• Google's Neural Machine Translation System: Bridging the Gap between Human and Machine Translation
• Deep Learning with Coherent Nanophotonic Circuits
• All-Optical Machine Learning Using Diffractive Deep Neural Networks
• Optical frequency comb generation from a monolithic microresonator
• Solving high-dimensional partial differential equations using deep learning
• High-Performance Hybrid Silicon and Lithium Niobate Mach-Zehnder Modulators for 100 Gbit/s and Beyond
• Universal Linear Optics
• Neuromorphic Silicon Photonic Networks
• Optoelectronic Reservoir Computing
• Extreme Broadband Transparent Optical Phase Change Materials for High-Performance Nonvolatile Photonics
• Nanophotonic Lithium Niobate Electro-optic Modulators
• All-optical Reservoir Computing
• Training of photonic neural networks through in situ backpropagation
• All Optical Neural Network with Nonlinear Activation Functions
• Fast inference of deep neural networks in FPGAs for particle physics
• Efficient, Compact and Low Loss Thermo-Optic Phase Shifter in Silicon
• Reinforcement Learning in a large scale photonic Recurrent Neural Network
• Long short-term memory networks in memristor crossbars
• Graphene Phase Modulator
• Reprogrammable Electro-Optic Nonlinear Activation Functions for Optical Neural Networks
• A silicon photonic modulator neuron
• Hybrid integration of silicon photonics circuits and InP lasers by photonic wire bonding
• Digital Electronics and Analog Photonics for Convolutional Neural Networks (DEAP-CNNs)
• Superconducting optoelectronic circuits for neuromorphic computing
• Toward Fast Neural Computing using All-Photonic Phase Change Spiking Neurons
• Dynamical laser spike processing
• Human action recognition with a large-scale brain-inspired photonic computer
• Tutorial: Photonic Neural Networks in Delay Systems
• Wavelength tuning and stabilization of microring-based filters using silicon in-resonator photoconductive heaters
• Solitary and Coupled Semiconductor Ring Lasers as Optical Spiking Neurons
• Neuromorphic photonics with electro-absorption modulators
• Machine learning for discriminating quantum measurement trajectories and improving readout
• All-silicon light-emitting diodes waveguide-integrated with superconducting single-photon detectors
• Excitability in semiconductor microring lasers: Experimental and theoretical pulse characterization
• Excitability in optical systems close to Z2-symmetry
• Electronic Bottleneck Suppression in Next-generation Networks with Integrated Photonic Digital-to-analog Converters
• Demonstration of multivariate photonics: blind dimensionality reduction with analog integrated photonics

Cited by in corpus (145)

• Single-chip photonic deep neural network for instantaneous image classification
• The physics of optical computing
• Applications of integrated optical microcombs
• Quantum networks based on color centers in diamond
• Intelligent Computing: The Latest Advances, Challenges and Future
• An optical neural network using less than 1 photon per multiplication
• Image sensing with multilayer, nonlinear optical neural networks
• On the use of deep learning for phase recovery
• Neuromorphic computing using wavelength-division multiplexing
• Prospects and applications of photonic neural networks
• High-order tensor flow processing using integrated photonic circuits
• Intelligent metaphotonics empowered by machine learning
• In-memory photonic dot-product engine with electrically programmable weight banks
• Silicon microring synapses enable photonic deep learning beyond 9-bit precision
• Intense optical parametric amplification in dispersion engineered nanophotonic lithium niobate waveguides
• Solving integral equations in free-space with inverse-designed ultrathin optical metagratings
• Optical coherent dot-product chip for sophisticated deep learning regression
• Polarization Multiplexed Diffractive Computing: All-Optical Implementation of a Group of Linear Transformations Through a Polarization-Encoded Diffractive Network
• Foundry manufacturing of tight-confinement, dispersion-engineered, ultralow-loss silicon nitride photonic integrated circuit
• Photonics for Neuromorphic Computing: Fundamentals, Devices, and Opportunities
• Why optics needs thickness
• Nonlinear optical encoding enabled by recurrent linear scattering
• Silicon Photonic Architecture for Training Deep Neural Networks with Direct Feedback Alignment
• Inverse-designed low-index-contrast structures on silicon photonics platform for vector-matrix multiplication
• Scaling Up Silicon Photonic-based Accelerators: Challenges and Opportunities
• Massively Parallel Universal Linear Transformations using a Wavelength-Multiplexed Diffractive Optical Network
• Artificial Neural Networks for Photonic Applications: From Algorithms to Implementation
• Applications and Techniques for Fast Machine Learning in Science
• Photonic spiking neural networks and CMOS-compatible graphene-on-silicon spiking neurons
• Integrated Photonic Tensor Processing Unit for a Matrix Multiply: a Review
• An Electro-Photonic System for Accelerating Deep Neural Networks
• Broadband physical layer cognitive radio with an integrated photonic processor for blind source separation
• Inverse-design of high-dimensional quantum optical circuits in a complex medium
• Six decades of the FitzHugh-Nagumo model: A guide through its spatio-temporal dynamics and influence across disciplines
• Optical Generative Models
• Stability of Self-Configuring Large Multiport Interferometers
• Scalability of all-optical neural networks based on spatial light modulators
• Foundry compatible, efficient wafer-scale manufacturing of ultra-low loss, high-density Si${}_3$N${}_4$ photonic integrated circuits
• Inverse Design of Grating Couplers Using the Policy Gradient Method from Reinforcement Learning
• An array of microresonators as a Photonic Extreme Learning Machine
• Fock State-enhanced Expressivity of Quantum Machine Learning Models
• Monadic Pavlovian associative learning in a backpropagation-free photonic network
• Ultrahigh-sensitivity optical power monitor for Si photonic circuits
• Optoelectronic Intelligence
• Energy-efficient neural network inference with microcavity exciton-polaritons
• Plug-Play Plasmonic Metafibers for Ultrafast Fiber Lasers
• Self-learning Machines based on Hamiltonian Echo Backpropagation
• Heavy tails and pruning in programmable photonic circuits
• A photonic complex perceptron for ultrafast data processing
• Inverse design of nano-photonic wavelength demultiplexer with a deep neural network approach
• Training neural networks with end-to-end optical backpropagation
• Complex-valued universal linear transformations and image encryption using spatially incoherent diffractive networks
• Surface Passivation of III-V GaAs Nanopillars by Low Frequency Plasma Deposition of Silicon Nitride for Active Nanophotonic Devices
• Multiscale simulations of growth-dominated Sb${}_2$Te phase-change material for non-volatile photonic applications
• Exciton Assisted Deeply Subwavelength Nano-Photonics
• Stimulated amplification of propagating spin waves
• Ultrafast single-channel machine vision based on neuro-inspired photonic computing
• Silicon photonic-electronic neural network for fibre nonlinearity compensation
• Deep Photonic Networks with Arbitrary and Broadband Functionality
• All-optical nonlinear activation function based on stimulated Brillouin scattering
• An optoacoustic field-programmable perceptron for recurrent neural networks
• Proposal for stable atom trapping on a GaN-on-Sapphire chip
• Mechanical intelligence via fully reconfigurable elastic neuromorphic metasurfaces
• Ultra-high endurance silicon photonic memory using vanadium dioxide
• Spiking Neural Network Nonlinear Demapping on Neuromorphic Hardware for IM/DD Optical Communication
• Contrasting the relative performance of RF photonic transversal signal processors based on microcombs using discrete components versus integrated devices
• Plasmon-enhanced optical control of magnetism at the nanoscale via the inverse Faraday effect
• All-Optical Image Identification with Programmable Matrix Transformation
• Demonstrating Analog Inference on the BrainScaleS-2 Mobile System
• Optical Neural Network Based on Synthetic Nonlinear Photonic Lattices
• Emergent self-adaptation in an integrated photonic neural network for backpropagation-free learning
• Waveguide-multiplexed photonic matrix-vector multiplication processor using multiport photodetectors
• Machine-Learning-Assisted Photonic Device Development: A Multiscale Approach from Theory to Characterization
• Nonlinear erasing of propagating spin-wave pulses in thin-film Ga:YIG
• Realistic quantum photonic neural networks
• Experimental demonstration of bandwidth enhancement in photonic time delay reservoir computing
• Flexible terahertz photonic light-cage modules for in-core sensing and high temperature applications
• Principles and Metrics of Extreme Learning Machines Using a Highly Nonlinear Fiber
• Artificial Spin Ice: A Tutorial on Design and Control of Geometry, Microstate, Magnon Dynamics & Neuromorphic Computing
• Learning Arbitrary Complex Matrices by Interlacing Amplitude and Phase Masks with Fixed Unitary Operations
• AnalogVNN: A fully modular framework for modeling and optimizing photonic neural networks
• Braided interferometer mesh for robust photonic matrix-vector multiplications with non-ideal components
• Sub-milliwatt threshold power and tunable-bias all-optical nonlinear activation function using vanadium dioxide for wavelength-division multiplexing photonic neural networks
• Neural Network Methods for Radiation Detectors and Imaging
• Programmable 200 GOPS Hopfield-inspired photonic Ising machine
• Silicon-organic hybrid thermo-optic switch based on a slot waveguide directional coupler
• Neural networks based on ultrafast time-delayed effects in exciton-polaritons
• Choose your tools carefully: A Comparative Evaluation of Deterministic vs. Stochastic and Binary vs. Analog Neuron models for Implementing Emerging Computing Paradigms
• Physical Neural Networks with Self-Learning Capabilities
• Artificial Nanophotonic Neuron with Internal Memory for Biologically Inspired and Reservoir Network Computing
• Inverse Design of Unitary Transmission Matrices in Silicon Photonic Coupled Waveguide Arrays using a Neural Adjoint Model
• Optically-triggered deterministic spiking regimes in nanostructure resonant tunnelling diode-photodetectors
• Mid-infrared single-photon computational temporal ghost imaging
• Massively parallel and universal approximation of nonlinear functions using diffractive processors
• Application of Reconfigurable All-Optical Activation Unit based on Optical Injection into Bistable Fabry-Pérot Laser in Multilayer Perceptron Neural Networks
• High-speed coherent photonic random-access memory in long-lasting sound waves
• Conflict-free joint sampling for preference satisfaction through quantum interference
• Thermally-robust spatiotemporal parallel reservoir computing by frequency filtering in frustrated magnets
• Beyond Weights: Deep learning in Spiking Neural Networks with pure synaptic-delay training
• Arbitrary control over multimode wave propagation for machine learning
• Photonic Matrix Multiplier Makes a Direction-Finding Sensor
• Inverted loss engineering in functional material covered waveguides
• Solving multi-armed bandit problems using a chaotic microresonator comb
• Merging and disconnecting resonance tongues in a pulsing excitable microlaser with delayed optical feedback
• Conflict-free joint decision by lag and zero-lag synchronization in laser network
• Extending the spectral operation of multimode and polarization-independent power splitters through subwavelength nanotechnology
• Self-pulsing dynamics in microscopic lasers with dispersive mirrors
• Excitability and memory in a time-delayed optoelectronic neuron
• Blending Optimal Control and Biologically Plausible Learning for Noise-Robust Physical Neural Networks
• Neuron-like spiking dynamics in the asymmetrically-driven dissipative photonic Bose-Hubbard dimer
• A 262 TOPS Hyperdimensional Photonic AI Accelerator powered by a Si3N4 microcomb laser
• Scalable intensity-based photonic matrix-vector multiplication processor using single-wavelength time-division-multiplexed signals
• Photonic systolic array for all-optical matrix-matrix multiplication
• Engineering nonlinear activation functions for all-optical neural networks via quantum interference
• Reservoir Computing based on Mutually Injected Phase Modulated Semiconductor Lasers as a monolithic integrated hardware accelerator
• All-Optical Excitable Spiking Laser Neuron in InP Generic Integration Technology
• Quantum optical classifier with superexponential speedup
• Coherence Awareness in Diffractive Neural Networks
• The Impact of Feature Representation on the Accuracy of Photonic Neural Networks
• Passive All-Optical Nonlinear Neuron Activation via PPLN Nanophotonic Waveguides
• Enhanced coupling between ballistic exciton-polariton condensates through tailored pumping
• Dense Associative Memory in a Nonlinear Optical Hopfield Neural Network
• Holographic photonic neuron
• Metalens array for complex-valued optical discrete Fourier transform
• Online training and pruning of multi-wavelength photonic neural networks
• Quantum-secure multiparty deep learning
• A self-learning magnetic Hopfield neural network with intrinsic gradient descent adaption
• Memristive, Spintronic, and 2D-Materials-Based Devices to Improve and Complement Computing Hardware
• Integrated magneto-photonic non-volatile multi-bit memory
• Perspective of high-speed Mach-Zehnder modulators based on nonlinear optics and complex band structures
• Quantum Transport Reservoir Computing
• Neural networks with quantum states of light
• An experimental demonstration of neuromorphic sensing of chemical species using electro-optical reservoir computing
• Shannon Entropy Helps Optimize the Performance of a Frequency-Multiplexed Extreme Learning Machine
• Slimmed optical neural networks with multiplexed neuron sets and a corresponding backpropagation training algorithm
• Optical Algorithm for Derivative of Real-Valued Functions
• Nonvolatile reconfigurable polarization rotator at datacom wavelengths based on a Sb2Se3/Si waveguide
• All-Optical Doubly Resonant Cavities for ReLU Function in Nanophotonic Deep Learning
• Experimental Investigation of Time Series Classification using a Self-Pulsing Microring Resonator Network
• Ultrafast neural sampling with spiking nanolasers
• 2022 Roadmap on Neuromorphic Computing and Engineering
• A Quarter of a Century of Neuromorphic Architectures on FPGAs -- an Overview
• Emergence of biased errors in imperfect photonic circuits
• Implementation of transformer-based LLMs with large-scale optoelectronic neurons on a CMOS compatible platform
• Integrated Photonic Devices in Thin-Film Barium Titanate: Opportunities and Challenges