Physical reservoir computing -- An introductory perspective

Abstract

Understanding the fundamental relationships between physics and its information-processing capability has been an active research topic for many years. Physical reservoir computing is a recently introduced framework that allows one to exploit the complex dynamics of physical systems as information-processing devices. This framework is particularly suited for edge computing devices, in which information processing is incorporated at the edge (e.g., into sensors) in a decentralized manner to reduce the adaptation delay caused by data transmission overhead. This paper aims to illustrate the potentials of the framework using examples from soft robotics and to provide a concise overview focusing on the basic motivations for introducing it, which stem from a number of fields, including machine learning, nonlinear dynamical systems, biological science, materials science, and physics.

18 pages, 8 figures

References in corpus (27)

• Overcoming catastrophic forgetting in neural networks
• Recent Advances in Physical Reservoir Computing: A Review
• Optoelectronic Reservoir Computing
• Complexity without chaos: Plasticity within random recurrent networks generates robust timing and motor control
• All-optical Reservoir Computing
• Reinforcement Learning in a large scale photonic Recurrent Neural Network
• Attractor Reconstruction by Machine Learning
• Harnessing disordered quantum dynamics for machine learning
• A magnetic skyrmion as a non-linear resistive element - a potential building block for reservoir computing
• Short-Term Memory in Orthogonal Neural Networks
• Quantum reservoir processing
• Analytical and Numerical Studies of Noise-induced Synchronization of Chaotic Systems
• Physical reservoir computing built by spintronic devices for temporal information processing
• Boosting computational power through spatial multiplexing in quantum reservoir computing
• full-FORCE: A Target-Based Method for Training Recurrent Networks
• Macromagnetic simulation for reservoir computing utilizing spin dynamics in magnetic tunnel junctions
• Reservoir computing with the frequency, phase and amplitude of spin-torque nano-oscillators
• Computing with Networks of Nonlinear Mechanical Oscillators
• Reservoir Computing on Spin-Torque Oscillator Array
• Optimal sequence memory in driven random networks
• A Substrate-Independent Framework to Characterise Reservoir Computers
• Temporal pattern recognition with delayed feedback spin-torque nano-oscillators
• Quantifying Morphological Computation
• Optimal short-term memory before the edge of chaos in driven random recurrent networks
• Synchronization and chaos in a spin-torque oscillator with a perpendicularly magnetized free layer
• Chaos in nanomagnet via feedback current
• Measuring information transfer in a soft robotic arm

Cited by in corpus (44)

• Nanoscale neural network using non-linear spin-wave interference
• Reconfigurable Training and Reservoir Computing in an Artificial Spin-Vortex Ice via Spin-Wave Fingerprinting
• Opportunities in Quantum Reservoir Computing and Extreme Learning Machines
• Temporal Information Processing on Noisy Quantum Computers
• Natural quantum reservoir computing for temporal information processing
• Implementing a magnonic time-delay reservoir computer model
• Pattern recognition with a magnon-scattering reservoir
• Designing spontaneous behavioral switching via chaotic itinerancy
• Reservoir Computing with Spin Waves in Skyrmion Crystal
• Realising and compressing quantum circuits with quantum reservoir computing
• Perspective on unconventional computing using magnetic skyrmions
• Spintronic reservoir computing without driving current or magnetic field
• The Reservoir Learning Power across Quantum Many-Boby Localization Transition
• Neural Schrödinger Equation:Physical Law as Neural Network
• Neuromorphic Overparameterisation and Few-Shot Learning in Multilayer Physical Neural Networks
• Periodic structure of memory function in spintronics reservoir with feedback current
• SpaRCe: Improved Learning of Reservoir Computing Systems through Sparse Representations
• Embedding bifurcations into pneumatic artificial muscle
• Step-like dependence of memory function on pulse width in spintronics reservoir computing
• Moire synaptic transistor for homogeneous-architecture reservoir computing
• Biomembrane-based Memcapacitive Reservoir Computing System for Energy Efficient Temporal Data Processing
• Handwritten Digit Recognition by Spin Waves in a Skyrmion Reservoir
• Machine Learning Potential of a Single Pendulum
• Self-starting nonlinear mode-locking in random lasers
• Extending echo state property for quantum reservoir computing
• Computational capability for physical reservoir computing using a spin-torque oscillator with two free layers
• Training Coupled Phase Oscillators as a Neuromorphic Platform using Equilibrium Propagation
• Input-driven chaotic dynamics in vortex spin-torque oscillator
• Learning unidirectional coupling using echo-state network
• Neural Echo State Network using oscillations of gas bubbles in water
• Photonic kernel machine learning for ultrafast spectral analysis
• Transient Chaos in BERT
• Evolving Programmable Computational Metamaterials
• Quantum reservoir computing on random regular graphs
• Universal Mechanical Polycomputation in Granular Matter
• Thermodynamic limit in learning period three
• Estimating many properties of a quantum state via quantum reservoir processing
• Attractor-merging Crises and Intermittency in Reservoir Computing
• Echoes of the Past: A Unified Perspective on Fading memory and Echo States
• High-Accuracy Temporal Prediction via Experimental Quantum Reservoir Computing in Correlated Spins
• Information processing via human soft tissue
• Incorporating Coupling Knowledge into Echo State Networks for Learning Spatiotemporally Chaotic Dynamics
• Neural networks with quantum states of light
• Memory Uncertainty Relation and Harmonic Memory in Random Recurrent Networks