Tutorial: Photonic Neural Networks in Delay Systems

Abstract

Photonic delay systems have revolutionized the hardware implementation of Recurrent Neural Networks and Reservoir Computing in particular. The fundamental principles of Reservoir Computing strongly benefit a realization in such complex analog systems. Especially delay systems, potentially providing large numbers of degrees of freedom even in simple architectures, can efficiently be exploited for information processing. The numerous demonstrations of their performance led to a revival of photonic Artificial Neural Network. Today, an astonishing variety of physical substrates, implementation techniques as well as network architectures based on this approach have been successfully employed. Important fundamental aspects of analog hardware Artificial Neural Networks have been investigated, and multiple high-performance applications have been demonstrated. Here, we introduce and explain the most relevant aspects of Artificial Neural Networks and delay systems, the seminal experimental demonstrations of Reservoir Computing in photonic delay systems, plus the most recent and advanced realizations.

References in corpus (16)

• Space Division Multiplexing in Optical Fibres
• Deep Learning with Coherent Nanophotonic Circuits
• Optoelectronic Reservoir Computing
• All-optical Reservoir Computing
• Reinforcement Learning in a large scale photonic Recurrent Neural Network
• High performance photonic reservoir computer based on a coherently driven passive cavity
• Broadband chaos generated by an opto-electronic oscillator
• Laser Chimeras as a paradigm for multi-stable patterns in complex systems
• Complex Dynamics and Synchronization of Delayed-Feedback Nonlinear Oscillators
• Online Training of an Opto-Electronic Reservoir Computer Applied to Real-Time Channel Equalisation
• Robustness of Optimal Synchronization in Real Networks
• Determination of phase noise spectra in optoelectronic microwave oscillators: a Langevin approach
• Using Synchronization for Prediction of High-Dimensional Chaotic Dynamics
• Brain-inspired photonic signal processor for periodic pattern generation and chaotic system emulation
• Embodiment of Learning in Electro-Optical Signal Processors
• Photonic Delay Systems as Machine Learning Implementations

Cited by in corpus (28)

• Recent Advances in Physical Reservoir Computing: A Review
• Photonics for artificial intelligence and neuromorphic computing
• Large-Scale Optical Reservoir Computing for Spatiotemporal Chaotic Systems Prediction
• Implementing a magnonic time-delay reservoir computer model
• Performance boost of time-delay reservoir computing by non-resonant clock cycle
• A Survey on Reservoir Computing and its Interdisciplinary Applications Beyond Traditional Machine Learning
• Coupled nonlinear delay systems as deep convolutional neural networks
• Insight into Delay Based Reservoir Computing via Eigenvalue Analysis
• Limitations of the recall capabilities in delay based reservoir computing systems
• Diffractive coupling for photonic networks: how big can we go?
• Model-Size Reduction for Reservoir Computing by Concatenating Internal States Through Time
• Optoelectronic Intelligence
• Wave-based extreme deep learning based on non-linear time-Floquet entanglement
• An optoacoustic field-programmable perceptron for recurrent neural networks
• Delay-induced self-oscillation excitation in the FitzHugh-Nagumo model: regular and chaotic dynamics
• Towards synthetic neural networks: Can artificial electrochemical neurons be coupled with artificial memristive synapses?
• Laminar Chaos in experiments and nonlinear delayed Langevin equations: A time series analysis toolbox for the detection of Laminar Chaos
• High-speed coherent photonic random-access memory in long-lasting sound waves
• Atom-by-atom construction of attractors in a tunable finite size spin array
• Deep Delay Loop Reservoir Computing for Specific Emitter Identification
• Role of non-linear data processing on speech recognition task in the framework of reservoir computing
• End-coupled random lasers: a basis for artificial neural networks
• Brillouin-based storage of QPSK signals with fully tunable phase retrieval
• Reservoir-Based Distributed Machine Learning for Edge Operation
• Shannon Entropy Helps Optimize the Performance of a Frequency-Multiplexed Extreme Learning Machine
• Efficient Reservoir Computing using Field Programmable Gate Array and Electro-optic Modulation
• Emergence of long-term rhythmicity within a frustrated triangle oscillator-network
• Infinite-dimensional Folded-in-time Deep Neural Networks