Optoelectronic Reservoir Computing

Abstract

Reservoir computing is a recently introduced, highly efficient bio-inspired approach for processing time dependent data. The basic scheme of reservoir computing consists of a non linear recurrent dynamical system coupled to a single input layer and a single output layer. Within these constraints many implementations are possible. Here we report an opto-electronic implementation of reservoir computing based on a recently proposed architecture consisting of a single non linear node and a delay line. Our implementation is sufficiently fast for real time information processing. We illustrate its performance on tasks of practical importance such as nonlinear channel equalization and speech recognition, and obtain results comparable to state of the art digital implementations.

Contains main paper and two Supplementary Materials

Cited by in corpus (113)

• Deep Learning with Coherent Nanophotonic Circuits
• Recent Advances in Physical Reservoir Computing: A Review
• Photonics for artificial intelligence and neuromorphic computing
• Integration of nanoscale memristor synapses in neuromorphic computing architectures
• All Optical Neural Network with Nonlinear Activation Functions
• Physical reservoir computing -- An introductory perspective
• Reinforcement Learning in a large scale photonic Recurrent Neural Network
• Large-Scale Optical Neural Networks based on Photoelectric Multiplication
• Harnessing disordered quantum dynamics for machine learning
• High performance photonic reservoir computer based on a coherently driven passive cavity
• Spiking Neural Networks Hardware Implementations and Challenges: a Survey
• Superconducting optoelectronic circuits for neuromorphic computing
• Neuromorphic computing using wavelength-division multiplexing
• Large-Scale Optical Reservoir Computing for Spatiotemporal Chaotic Systems Prediction
• Human action recognition with a large-scale brain-inspired photonic computer
• Design of optical neural networks with component imprecisions
• Quantum reservoir processing
• Reservoir Computing with Random Skyrmion Textures
• Tutorial: Photonic Neural Networks in Delay Systems
• Physical reservoir computing built by spintronic devices for temporal information processing
• Macromagnetic simulation for reservoir computing utilizing spin dynamics in magnetic tunnel junctions
• Reservoir computing with a single time-delay autonomous Boolean node
• Optical Reservoir Computing using multiple light scattering for chaotic systems prediction
• Reservoir computing with the frequency, phase and amplitude of spin-torque nano-oscillators
• Computing with Networks of Nonlinear Mechanical Oscillators
• Quantum reservoir computing with a single nonlinear oscillator
• Pattern recognition with neuromorphic computing using magnetic-field induced dynamics of skyrmions
• Quantum neuromorphic computing
• Using a reservoir computer to learn chaotic attractors, with applications to chaos synchronisation and cryptography
• Reservoir Computing on Spin-Torque Oscillator Array
• Demonstrating Delay-based Reservoir Computing Using a Compact Photonic Integrated Chip
• A Substrate-Independent Framework to Characterise Reservoir Computers
• Online Training of an Opto-Electronic Reservoir Computer Applied to Real-Time Channel Equalisation
• Reservoir computing based on a silicon microring and time multiplexing for binary and analog operations
• Temporal pattern recognition with delayed feedback spin-torque nano-oscillators
• Machine learning algorithms for predicting the amplitude of chaotic laser pulses
• Implementing a magnonic time-delay reservoir computer model
• Trainable and Dynamic Computing: Error Backpropagation through Physical Media
• Pattern recognition with a magnon-scattering reservoir
• Microfabricated Neuroaccelerometer: Integrating Sensing and Reservoir Computing in MEMS
• Large-scale spatiotemporal photonic reservoir computer for image classification
• A Survey on Reservoir Computing and its Interdisciplinary Applications Beyond Traditional Machine Learning
• Neuromorphic Time-Dependent Pattern Classification with Organic Electrochemical Transistor Arrays
• All-Optical Spiking Neuron Based On Passive Micro-Resonator
• Reservoir Computing with Diverse Timescales for Prediction of Multiscale Dynamics
• Spin waves propagating through a stripe magnetic domain structure and their applications to reservoir computing
• Deep Neural Networks using a Single Neuron: Folded-in-Time Architecture using Feedback-Modulated Delay Loops
• Coupled nonlinear delay systems as deep convolutional neural networks
• Brain-inspired photonic signal processor for periodic pattern generation and chaotic system emulation
• Delayed Dynamical Systems: Networks, Chimeras and Reservoir Computing
• Mean Field Theory of Dynamical Systems Driven by External Signals
• Reservoir Computing with Spin Waves in Skyrmion Crystal
• Reconfigurable Reservoir Computing in a Magnetic Metamaterial
• Time-Delay Polaritonics
• PAM-4 Transmission at 1550nm using Photonic Reservoir Computing Post-processing
• Embodiment of Learning in Electro-Optical Signal Processors
• Memristor models for machine learning
• Reservoir computing with simple oscillators: Virtual and real networks
• Spintronic reservoir computing without driving current or magnetic field
• Simulation platform for pattern recognition based on reservoir computing with memristor networks
• Developing of a photonic hardware platform for brain-inspired computing based on $5\times 5$ VCSEL arrays
• Experiments with arbitrary networks in time-multiplexed delay systems
• Principles of Neuromorphic Photonics
• Photonic Extreme Learning Machine based on frequency multiplexing
• Robust Forecasting using Predictive Generalized Synchronization in Reservoir Computing
• Insight into Delay Based Reservoir Computing via Eigenvalue Analysis
• Photonic reservoir computer based on frequency multiplexing
• Limitations of the recall capabilities in delay based reservoir computing systems
• Computing matrix inversion with optical networks
• CONDENSE: A Reconfigurable Knowledge Acquisition Architecture for Future 5G IoT
• Reservoir Computing Benchmarks: a tutorial review and critique
• Diffractive coupling for photonic networks: how big can we go?
• SpaRCe: Improved Learning of Reservoir Computing Systems through Sparse Representations
• Handwritten Digit Recognition by Spin Waves in a Skyrmion Reservoir
• Ultrafast single-channel machine vision based on neuro-inspired photonic computing
• Effects of cavity nonlinearities and linear losses on silicon microring-based reservoir computing
• Photonic reservoir computing enabled by stimulated Brillouin scattering
• Machine Learning Link Inference of Noisy Delay-coupled Networks with Opto-Electronic Experimental Tests
• Photons guided by axons may enable backpropagation-based learning in the brain
• Chaotic attractor reconstruction using small reservoirs -- the influence of topology
• Dissipative solitons for bistable delayed-feedback systems
• Time-Delayed Reservoir Computing Based on Dual-Waveband Quantum-Dot Spin-Polarized Vertical Cavity Surface-Emitting Laser
• Skyrmion based energy efficient straintronic physical reservoir computing
• Deep Photonic Reservoir Computer for Speech Recognition
• Online training for high-performance analogue readout layers in photonic reservoir computers
• Short-wavelength Reverberant Wave Systems for Physical Realization of Reservoir Computing
• Experimental demonstration of bandwidth enhancement in photonic time delay reservoir computing
• Nonlinear Inference Capacity of Fiber-Optical Extreme Learning Machines
• Photonic kernel machine learning for ultrafast spectral analysis
• Practical Few-Atom Quantum Reservoir Computing
• Pseudo-laminar chaos from on-off intermittency
• Special Session: Neuromorphic hardware design and reliability from traditional CMOS to emerging technologies
• Optical integration of a real-valued function by measurement of a Stokes Parameter
• Optical Neural Ordinary Differential Equations
• Time-shift selection for reservoir computing using a rank-revealing QR algorithm
• Non-spectroscopic sensing enabled by electro-optical reservoir computer
• Comparison of echo state network output layer classification methods on noisy data
• 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
• Thermally-robust spatiotemporal parallel reservoir computing by frequency filtering in frustrated magnets
• High-resolution dynamic consistency analysis of photonic time-delay reservoir computer
• Chaotic magnetization dynamics in magnetic Duffing oscillator
• Hardware-Friendly Implementation of Physical Reservoir Computing with CMOS-based Time-domain Analog Spiking Neurons
• Role of non-linear data processing on speech recognition task in the framework of reservoir computing
• Spintronic Physical Reservoir for Autonomous Prediction and Long-Term Household Energy Load Forecasting
• Numerical Solution and Bifurcation Analysis of Nonlinear Partial Differential Equations with Extreme Learning Machines
• Magneto-Ionic Physical Reservoir Computing
• Exploring Non-Steady-State Charge Transport Dynamics in Information Processing: Insights from Reservoir Computing
• Analysis of temporal structure of laser chaos by Allan variance
• Metrics for spin-based computing
• An experimental demonstration of neuromorphic sensing of chemical species using electro-optical reservoir computing
• A magnonic-optoelectronic reservoir for physical reservoir computing
• The Role of Entanglement in Quantum Reservoir Computing with Coupled Kerr Nonlinear Oscillators