A Survey on Reservoir Computing and its Interdisciplinary Applications Beyond Traditional Machine Learning

Abstract

Reservoir computing (RC), first applied to temporal signal processing, is a recurrent neural network in which neurons are randomly connected. Once initialized, the connection strengths remain unchanged. Such a simple structure turns RC into a non-linear dynamical system that maps low-dimensional inputs into a high-dimensional space. The model's rich dynamics, linear separability, and memory capacity then enable a simple linear readout to generate adequate responses for various applications. RC spans areas far beyond machine learning, since it has been shown that the complex dynamics can be realized in various physical hardware implementations and biological devices. This yields greater flexibility and shorter computation time. Moreover, the neuronal responses triggered by the model's dynamics shed light on understanding brain mechanisms that also exploit similar dynamical processes. While the literature on RC is vast and fragmented, here we conduct a unified review of RC's recent developments from machine learning to physics, biology, and neuroscience. We first review the early RC models, and then survey the state-of-the-art models and their applications. We further introduce studies on modeling the brain's mechanisms by RC. Finally, we offer new perspectives on RC development, including reservoir design, coding frameworks unification, physical RC implementations, and interaction between RC, cognitive neuroscience and evolution.

arXiv comment51 pages, 19 figures, IEEE Access

References in corpus (51)

• Explaining and Harnessing Adversarial Examples
• Advances in the Physics of Magnetic Skyrmions and Perspective for Technology
• Recent Advances in Physical Reservoir Computing: A Review
• One pixel attack for fooling deep neural networks
• A Review on Deep Learning Techniques Applied to Semantic Segmentation
• Optoelectronic Reservoir Computing
• Machine Learning Methods for Attack Detection in the Smart Grid
• Next Generation Reservoir Computing
• Complexity without chaos: Plasticity within random recurrent networks generates robust timing and motor control
• All-optical Reservoir Computing
• Cellular-Connected UAVs over 5G: Deep Reinforcement Learning for Interference Management
• Harnessing disordered quantum dynamics for machine learning
• A magnetic skyrmion as a non-linear resistive element - a potential building block for reservoir computing
• Phase reduction approach to synchronization of nonlinear oscillators
• High performance photonic reservoir computer based on a coherently driven passive cavity
• Supervised Learning in Spiking Neural Networks with FORCE Training
• On Explaining the Surprising Success of Reservoir Computing Forecaster of Chaos? The Universal Machine Learning Dynamical System with Contrasts to VAR and DMD
• Opportunities in Quantum Reservoir Computing and Extreme Learning Machines
• Tutorial: Photonic Neural Networks in Delay Systems
• Potential implementation of Reservoir Computing models based on magnetic skyrmions
• 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 a single time-delay autonomous Boolean node
• Computing with Networks of Nonlinear Mechanical Oscillators
• Quantum reservoir computing with a single nonlinear oscillator
• Dynamical phase transitions in quantum reservoir computing
• Control of criticality and computation in spiking neuromorphic networks with plasticity
• Network Structure Effects in Reservoir Computers
• Biologically inspired alternatives to backpropagation through time for learning in recurrent neural nets
• Computational Capabilities of Random Automata Networks for Reservoir Computing
• Spin waves propagating through a stripe magnetic domain structure and their applications to reservoir computing
• Echo State Networks trained by Tikhonov least squares are L2(μ) approximators of ergodic dynamical systems
• Beyond exploding and vanishing gradients: analysing RNN training using attractors and smoothness
• Realising and compressing quantum circuits with quantum reservoir computing
• Memristor models for machine learning
• Spintronic reservoir computing without driving current or magnetic field
• Neural Schrödinger Equation:Physical Law as Neural Network
• Scaling up Echo-State Networks with multiple light scattering
• Reservoirs learn to learn
• Signals to Spikes for Neuromorphic Regulated Reservoir Computing and EMG Hand Gesture Recognition
• ReservoirComputing.jl: An Efficient and Modular Library for Reservoir Computing Models
• Deep Reservoir Computing Using Cellular Automata
• Populations of Spiking Neurons for Reservoir Computing: Closed Loop Control of a Compliant Quadruped
• Reservoir Computing using High Order Synchronization of Coupled Oscillators
• Reservoir Memory Machines as Neural Computers
• Reservoir Computing Hardware with Cellular Automata
• Deep Delay Loop Reservoir Computing for Specific Emitter Identification
• Road traffic reservoir computing
• R-FORCE: Robust Learning for Random Recurrent Neural Networks
• Generating Oscillation Activity with Echo State Network to Mimic the Behavior of a Simple Central Pattern Generator

Cited by in corpus (3)

• Evaluation of Bio-Inspired Models under Different Learning Settings For Energy Efficiency in Network Traffic Prediction
• Learning Music Audio Representations With Limited Data
• Multi-agent reinforcement learning using echo-state network and its application to pedestrian dynamics