Reinforcement Learning in a large scale photonic Recurrent Neural Network

Abstract

Photonic Neural Network implementations have been gaining considerable attention as a potentially disruptive future technology. Demonstrating learning in large scale neural networks is essential to establish photonic machine learning substrates as viable information processing systems. Realizing photonic Neural Networks with numerous nonlinear nodes in a fully parallel and efficient learning hardware was lacking so far. We demonstrate a network of up to 2500 diffractively coupled photonic nodes, forming a large scale Recurrent Neural Network. Using a Digital Micro Mirror Device, we realize reinforcement learning. Our scheme is fully parallel, and the passive weights maximize energy efficiency and bandwidth. The computational output efficiently converges and we achieve very good performance.

References in corpus (1)

• Online training for high-performance analogue readout layers in photonic reservoir computers

Cited by in corpus (89)

• Recent Advances in Physical Reservoir Computing: A Review
• Photonics for artificial intelligence and neuromorphic computing
• Deep physical neural networks enabled by a backpropagation algorithm for arbitrary physical systems
• Single-chip photonic deep neural network for instantaneous image classification
• Large-scale neuromorphic optoelectronic computing with a reconfigurable diffractive processing unit
• All Optical Neural Network with Nonlinear Activation Functions
• Physical reservoir computing -- An introductory perspective
• Intelligent Nanophotonics: Merging Photonics and Artificial Intelligence at the Nanoscale
• Intelligent Computing: The Latest Advances, Challenges and Future
• An optical neural network using less than 1 photon per multiplication
• Analysis of Diffractive Optical Neural Networks and Their Integration with Electronic Neural Networks
• Spectrally-Encoded Single-Pixel Machine Vision Using Diffractive Networks
• Single chip photonic deep neural network with accelerated training
• Neuromorphic computing using wavelength-division multiplexing
• Large-Scale Optical Reservoir Computing for Spatiotemporal Chaotic Systems Prediction
• Theory of neuromorphic computing by waves: machine learning by rogue waves, dispersive shocks, and solitons
• Prospects and applications of photonic neural networks
• Human action recognition with a large-scale brain-inspired photonic computer
• Terahertz Pulse Shaping Using Diffractive Surfaces
• Class-specific Differential Detection in Diffractive Optical Neural Networks Improves Inference Accuracy
• Tutorial: Photonic Neural Networks in Delay Systems
• All-Optical Information Processing Capacity of Diffractive Surfaces
• Misalignment Resilient Diffractive Optical Networks
• Ensemble learning of diffractive optical networks
• Optical Reservoir Computing using multiple light scattering for chaotic systems prediction
• 8x8 Reconfigurable quantum photonic processor based on silicon nitride waveguides
• Polarization Multiplexed Diffractive Computing: All-Optical Implementation of a Group of Linear Transformations Through a Polarization-Encoded Diffractive Network
• An Optical Frontend for a Convolutional Neural Network
• Photonic extreme learning machine by free-space optical propagation
• Massively Parallel Universal Linear Transformations using a Wavelength-Multiplexed Diffractive Optical Network
• Reservoir computing based on a silicon microring and time multiplexing for binary and analog operations
• Scale-, shift- and rotation-invariant diffractive optical networks
• Artificial Neural Networks for Photonic Applications: From Algorithms to Implementation
• Noise-enhanced spatial-photonic Ising machine
• Efficient training and design of photonic neural network through neuroevolution
• Large-scale spatiotemporal photonic reservoir computer for image classification
• Scalable spin-glass optical simulator
• Coupled nonlinear delay systems as deep convolutional neural networks
• Classification of time-domain waveforms using a speckle-based optical reservoir computer
• Delayed Dynamical Systems: Networks, Chimeras and Reservoir Computing
• Understanding and mitigating noise in trained deep neural networks
• Developing of a photonic hardware platform for brain-inspired computing based on $5\times 5$ VCSEL arrays
• Fundamental aspects of noise in analog-hardware neural networks
• Photonic reservoir computer based on frequency multiplexing
• Insight into Delay Based Reservoir Computing via Eigenvalue Analysis
• Diffractive coupling for photonic networks: how big can we go?
• Knowledge Distillation Circumvents Nonlinearity for Optical Convolutional Neural Networks
• High Speed Human Action Recognition using a Photonic Reservoir Computer
• Energy-efficient neural network inference with microcavity exciton-polaritons
• A Broad-Spectrum Diffractive Network via Ensemble Learning
• Wave-based extreme deep learning based on non-linear time-Floquet entanglement
• Entangled-photon decision maker
• Silicon photonic-electronic neural network for fibre nonlinearity compensation
• Experimental reservoir computing with diffractively coupled VCSELs
• An optoacoustic field-programmable perceptron for recurrent neural networks
• Training Coupled Phase Oscillators as a Neuromorphic Platform using Equilibrium Propagation
• Deep Photonic Reservoir Computer for Speech Recognition
• Spatial-photonic Ising machine by space-division multiplexing with physically tunable coefficients of a multi-component model
• Boolean learning under noise-perturbations in hardware neural networks
• Noise mitigation strategies in physical feedforward neural networks
• Two-color optically-addressed spatial light modulator as generic spatio-temporal systems
• Optical convolutional neural network with atomic nonlinearity
• Nanophotonic Media for Artificial Neural Inference
• High-performance real-world optical computing trained by in situ gradient-based model-free optimization
• Neural networks based on ultrafast time-delayed effects in exciton-polaritons
• Automated Design and Optimization of Distributed Filtering Circuits via Reinforcement Learning
• Injection locking and coupling the emitters of large VCSEL arrays via diffraction in an external cavity
• Impact of white noise in artificial neural networks trained for classification: performance and noise mitigation strategies
• Advancing Fourier: space-time concepts in ultrafast optics, imaging and photonic neural networks
• Image classification using collective optical modes of an array of nanolasers
• Backpropagation through nonlinear units for all-optical training of neural networks
• Theory of Quantum Path Computing with Fourier Optics and Future Applications for Quantum Supremacy, Neural Networks and Nonlinear Schrödinger Equations
• Model-free Optical Processors using In Situ Reinforcement Learning with Proximal Policy Optimization
• Training and pattern recognition by an opto-magnetic neural network
• Conflict-free joint decision by lag and zero-lag synchronization in laser network
• A spiking photonic neural network of 40.000 neurons, trained with rank-order coding for leveraging sparsity
• Impact of internal noise on convolutional neural networks
• Synergic quantum generative machine learning
• Predicting quantum evolutions of excitation energy transfer in a light-harvesting complex using multi-optimized recurrent neural networks
• Adiabatic evolution on a spatial-photonic Ising machine
• Performance evaluation of an integrated photonic convolutional neural network based on delay buffering and wavelength division multiplexing
• Experimental kernel-based quantum machine learning in finite feature space
• Noise impact on recurrent neural network with linear activation function
• End-to-End Framework for Efficient Deep Learning Using Metasurfaces Optics
• Adaptive model selection in photonic reservoir computing by reinforcement learning
• Resonant tunnelling diode nano-optoelectronic spiking nodes for neuromorphic information processing
• Using multidimensional speckle dynamics for high-speed, large-scale, parallel photonic computing
• Optical Proof of Work
• Implementation of Optical Deep Neural Networks using the Fabry-Perot Interferometer