All-optical Reservoir Computing

Abstract

Reservoir Computing is a novel computing paradigm which uses a nonlinear recurrent dynamical system to carry out information processing. Recent electronic and optoelectronic Reservoir Computers based on an architecture with a single nonlinear node and a delay loop have shown performance on standardized tasks comparable to state-of-the-art digital implementations. Here we report an all-optical implementation of a Reservoir Computer, made of off-the-shelf components for optical telecommunications. It uses the saturation of a semiconductor optical amplifier as nonlinearity. The present work shows that, within the Reservoir Computing paradigm, all-optical computing with state-of-the-art performance is possible.

Cited by in corpus (64)

• Recent Advances in Physical Reservoir Computing: A Review
• Photonics for artificial intelligence and neuromorphic computing
• All Optical Neural Network with Nonlinear Activation Functions
• Physical reservoir computing -- An introductory perspective
• Reinforcement Learning in a large scale photonic Recurrent Neural Network
• High performance photonic reservoir computer based on a coherently driven passive cavity
• Neuromorphic computing using wavelength-division multiplexing
• Theory of neuromorphic computing by waves: machine learning by rogue waves, dispersive shocks, and solitons
• Human action recognition with a large-scale brain-inspired photonic computer
• Quantum reservoir processing
• Tutorial: Photonic Neural Networks in Delay Systems
• Experimental quantum memristor
• Three dimensional waveguide-interconnects for scalable integration of photonic neural networks
• Computing with Networks of Nonlinear Mechanical Oscillators
• Gaussian states of continuous-variable quantum systems provide universal and versatile reservoir computing
• A Substrate-Independent Framework to Characterise Reservoir Computers
• Online Training of an Opto-Electronic Reservoir Computer Applied to Real-Time Channel Equalisation
• Rapid Time Series Prediction with a Hardware-Based Reservoir Computer
• Temporal pattern recognition with delayed feedback spin-torque nano-oscillators
• Large-scale spatiotemporal photonic reservoir computer for image classification
• A Survey on Reservoir Computing and its Interdisciplinary Applications Beyond Traditional Machine Learning
• Spin waves propagating through a stripe magnetic domain structure and their applications to reservoir computing
• Fabry-Perot Lasers as Enablers for Parallel Reservoir Computing
• Deep Neural Networks using a Single Neuron: Folded-in-Time Architecture using Feedback-Modulated Delay Loops
• Brain-inspired photonic signal processor for periodic pattern generation and chaotic system emulation
• Classification of time-domain waveforms using a speckle-based optical reservoir computer
• Reservoir Computing with Spin Waves in Skyrmion Crystal
• Manifold Learning for Knowledge Discovery and Intelligent Inverse Design of Photonic Nanostructures: Breaking the Geometric Complexity
• Efficient Design of Hardware-Enabled Reservoir Computing in FPGAs
• Scalability of all-optical neural networks based on spatial light modulators
• Principles of Neuromorphic Photonics
• Photonic Extreme Learning Machine based on frequency multiplexing
• Photonic reservoir computer based on frequency multiplexing
• Reservoir Computing Benchmarks: a tutorial review and critique
• Diffractive coupling for photonic networks: how big can we go?
• High Speed Human Action Recognition using a Photonic Reservoir Computer
• A photonic complex perceptron for ultrafast data processing
• Handwritten Digit Recognition by Spin Waves in a Skyrmion Reservoir
• Photonic reservoir computing enabled by stimulated Brillouin scattering
• Effects of cavity nonlinearities and linear losses on silicon microring-based reservoir computing
• Photons guided by axons may enable backpropagation-based learning in the brain
• Training Coupled Phase Oscillators as a Neuromorphic Platform using Equilibrium Propagation
• Spatial Analysis of Physical Reservoir Computers
• Boolean learning under noise-perturbations in hardware neural networks
• Online training for high-performance analogue readout layers in photonic reservoir computers
• Nonlinear Inference Capacity of Fiber-Optical Extreme Learning Machines
• Photonic kernel machine learning for ultrafast spectral analysis
• Designs toward synchronization of optical limit cycles with coupled silicon photonic crystal microcavities
• Thermally-robust spatiotemporal parallel reservoir computing by frequency filtering in frustrated magnets
• High-resolution dynamic consistency analysis of photonic time-delay reservoir computer
• Multi-task Photonic Reservoir Computing: Wavelength Division Multiplexing for Parallel Computing with a Silicon Microring Resonator
• Random pattern and frequency generation using a photonic reservoir computer with output feedback
• Limits of nonlinear and dispersive fiber propagation for an optical fiber-based extreme learning machine
• Role of non-linear data processing on speech recognition task in the framework of reservoir computing
• Hardware-Friendly Implementation of Physical Reservoir Computing with CMOS-based Time-domain Analog Spiking Neurons
• Model-free Optical Processors using In Situ Reinforcement Learning with Proximal Policy Optimization
• Quantum Reservoir Computing for Realized Volatility Forecasting
• Generating Quantum Reservoir State Representations with Random Matrices
• Metrics for spin-based computing
• An experimental demonstration of neuromorphic sensing of chemical species using electro-optical reservoir computing
• Predicting the future with magnons
• The Role of Entanglement in Quantum Reservoir Computing with Coupled Kerr Nonlinear Oscillators
• Programming multi-level quantum gates in disordered computing reservoirs via machine learning and TensorFlow
• All-Optical Synthesis of an Arbitrary Linear Transformation Using Diffractive Surfaces