High performance photonic reservoir computer based on a coherently driven passive cavity

Abstract

Reservoir computing is a recent bio-inspired approach for processing time-dependent signals. It has enabled a breakthrough in analog information processing, with several experiments, both electronic and optical, demonstrating state-of-the-art performances for hard tasks such as speech recognition, time series prediction and nonlinear channel equalization. A proof-of-principle experiment using a linear optical circuit on a photonic chip to process digital signals was recently reported. Here we present a photonic implementation of a reservoir computer based on a coherently driven passive fiber cavity processing analog signals. Our experiment has error rate as low or lower than previous experiments on a wide variety of tasks, and also has lower power consumption. Furthermore, the analytical model describing our experiment is also of interest, as it constitutes a very simple high performance reservoir computer algorithm. The present experiment, given its good performances, low energy consumption and conceptual simplicity, confirms the great potential of photonic reservoir computing for information processing applications ranging from artificial intelligence to telecommunications

none

References in corpus (4)

• Optoelectronic Reservoir Computing
• All-optical Reservoir Computing
• Photonic Delay Systems as Machine Learning Implementations
• Analog readout for optical reservoir computers

Cited by in corpus (46)

• Recent Advances in Physical Reservoir Computing: A Review
• Large-Scale Optical Reservoir Computing for Spatiotemporal Chaotic Systems Prediction
• Human action recognition with a large-scale brain-inspired photonic computer
• Tutorial: Photonic Neural Networks in Delay Systems
• Polaritonic neuromorphic computing outperforms linear classifiers
• Temporal Information Processing on Noisy Quantum Computers
• Photonic extreme learning machine by free-space optical propagation
• Reservoir computing based on a silicon microring and time multiplexing for binary and analog operations
• Online Training of an Opto-Electronic Reservoir Computer Applied to Real-Time Channel Equalisation
• Temporal pattern recognition with delayed feedback spin-torque nano-oscillators
• Super cavity solitons and the coexistence of multiple nonlinear states in a tristable passive Kerr resonator
• A Survey on Reservoir Computing and its Interdisciplinary Applications Beyond Traditional Machine Learning
• Combining Machine Learning with Knowledge-Based Modeling for Scalable Forecasting and Subgrid-Scale Closure of Large, Complex, Spatiotemporal Systems
• Deep Neural Networks using a Single Neuron: Folded-in-Time Architecture using Feedback-Modulated Delay Loops
• Classification of time-domain waveforms using a speckle-based optical reservoir computer
• Brain-inspired photonic signal processor for periodic pattern generation and chaotic system emulation
• High Speed Photonic Neuromorphic Computing Using Recurrent Optical Spectrum Slicing Neural Networks
• PAM-4 Transmission at 1550nm using Photonic Reservoir Computing Post-processing
• Deep Photonic Reservoir Computer Based on Frequency Multiplexing with Fully Analog Connection Between Layers
• Embodiment of Learning in Electro-Optical Signal Processors
• Reservoir computing with simple oscillators: Virtual and real networks
• Photonic Extreme Learning Machine based on frequency multiplexing
• Photonic reservoir computer based on frequency multiplexing
• Insight into Delay Based Reservoir Computing via Eigenvalue Analysis
• Limitations of the recall capabilities in delay based reservoir computing systems
• Learning unseen coexisting attractors
• Reservoir Computing Benchmarks: a tutorial review and critique
• Spatio-temporal complexity in dual delay nonlinear laser dynamics: chimeras and dissipative solitons
• High Speed Human Action Recognition using a Photonic Reservoir Computer
• Machine Learning Link Inference of Noisy Delay-coupled Networks with Opto-Electronic Experimental Tests
• Modeling quasi-dark states with Temporal Coupled-Mode Theory
• Risk bounds for reservoir computing
• Gigahertz-rate random speckle projection for high-speed single-pixel image classification
• Stability Analysis of Reservoir Computers Dynamics via Lyapunov Functions
• Deep Photonic Reservoir Computer for Speech Recognition
• Reservoir Computers with Random and Optimized Time-Shifts
• Online training for high-performance analogue readout layers in photonic reservoir computers
• Random pattern and frequency generation using a photonic reservoir computer with output feedback
• Role of non-linear data processing on speech recognition task in the framework of reservoir computing
• Universal discrete-time reservoir computers with stochastic inputs and linear readouts using non-homogeneous state-affine systems
• Differentiable reservoir computing
• Photonic neural field on a silicon chip: large-scale, high-speed neuro-inspired computing and sensing
• Reservoir Computers Modal Decomposition and Optimization
• Microring resonators with external optical feedback for time delay reservoir computing
• Quantum Transport Reservoir Computing
• All-optical spiking neurosynaptic networks with self-learning capabilities