Reservoir computing approaches to recurrent neural network training

DOI10.1016/J.COSREV.2009.03.005zbMATH Open1302.68235OpenAlexW2171865010WikidataQ105583675 ScholiaQ105583675MaRDI QIDQ458488FDOQ458488

Authors: Mantas Lukoševičius, Herbert Jaeger 

Publication date: 7 October 2014

Published in: Computer Science Review (Search for Journal in Brave)

Full work available at URL: https://doi.org/10.1016/j.cosrev.2009.03.005

Recommendations

• An experimental unification of reservoir computing methods
• Reservoir computing with computational matter
• Deep reservoir computing
• Echo state networks with filter neurons and a delay\&sum readout
• Recurrent kernel machines: computing with infinite echo state networks

zbMATH Keywords

recurrent neural networksreservoir computing

Mathematics Subject Classification ID

Learning and adaptive systems in artificial intelligence (68T05) Research exposition (monographs, survey articles) pertaining to computer science (68-02) Neural networks for/in biological studies, artificial life and related topics (92B20)

Cites Work

• Training Recurrent Networks by Evolino
• Reducing the Dimensionality of Data with Neural Networks
• Emergence of Scaling in Random Networks
• Collective dynamics of `small-world' networks
• Title not available (Why is that?)
• Neural networks and physical systems with emergent collective computational abilities
• Title not available (Why is that?)
• Synergies Between Intrinsic and Synaptic Plasticity Mechanisms
• Optimization and applications of echo state networks with leaky- integrator neurons
• Real-Time Computing Without Stable States: A New Framework for Neural Computation Based on Perturbations
• An experimental unification of reservoir computing methods
• Isolated word recognition with the Liquid State Machine: a case study
• Complex sensory-motor sequence learning based on recurrent state representation and reinforcement learning
• The cerebellum as a liquid state machine
• Fading memory and time series prediction in recurrent networks with different forms of plasticity
• Edge of chaos and prediction of computational performance for neural circuit models
• Online reservoir adaptation by intrinsic plasticity for backpropagation-decorrelation and echo state learning
• Decoupled echo state networks with lateral inhibition
• An associative memory readout for ESNs with applications to dynamical pattern recognition
• Automatic speech recognition using a predictive echo state network classifier
• Modular echo state neural networks in time series prediction
• Reservoir optimization in recurrent neural networks using properties of Kronecker product
• Spiking Neurons Can Learn to Solve Information Bottleneck Problems and Extract Independent Components
• Dynamical Working Memory and Timed Responses: The Role of Reverberating Loops in the Olivo-Cerebellar System
• Real-Time Computation at the Edge of Chaos in Recurrent Neural Networks
• Analysis and Design of Echo State Networks

Cited In (only showing first 100 items - show all)

• Homeostatic plasticity for single node delay-coupled reservoir computing
• Learning strange attractors with reservoir systems
• Two methods to approximate the Koopman operator with a reservoir computer
• Echo state networks are universal
• Machine-learning construction of a model for a macroscopic fluid variable using the delay-coordinate of a scalar observable
• Echo state property linked to an input: exploring a fundamental characteristic of recurrent neural networks
• Deep reservoir computing
• A multiscale multi-permeability poroplasticity model linked by recursive homogenizations and deep learning
• Spiking networks as efficient distributed controllers
• Stabilized neural ordinary differential equations for long-time forecasting of dynamical systems
• Dynamical systems as temporal feature spaces
• Comparison of echo state network and feed-forward neural networks in electrical load forecasting for demand response programs
• Functional echo state network for time series classification
• Reservoir optimization in recurrent neural networks using properties of Kronecker product
• An experimental unification of reservoir computing methods
• Deep reservoir neural networks for trees
• A local echo state property through the largest Lyapunov exponent
• Learning nonlinear input-output maps with dissipative quantum systems
• Detecting unstable periodic orbits based only on time series: when adaptive delayed feedback control meets reservoir computing
• Good and bad predictions: assessing and improving the replication of chaotic attractors by means of reservoir computing
• Transport in reservoir computing
• Timescale separation in recurrent neural networks
• The echo index and multistability in input-driven recurrent neural networks
• Design strategies for weight matrices of echo state networks
• A reservoir-driven non-stationary hidden Markov model
• Delay-dependent stability analysis of the QUAD vector field fractional order quaternion-valued memristive uncertain neutral type leaky integrator echo state neural networks
• A modified batch intrinsic plasticity method for pre-training the random coefficients of extreme learning machines
• Functional identification of biological neural networks using reservoir adaptation for point processes
• Solving flows of dynamical systems by deep neural networks and a novel deep learning algorithm
• Training Recurrent Networks by Evolino
• A framework for machine learning of model error in dynamical systems
• Using reservoir computer to predict and prevent extreme events
• \(\mathrm{SO}(3)\)-invariance of informed-graph-based deep neural network for anisotropic elastoplastic materials
• Title not available (Why is that?)
• Relative entropy minimizing noisy non-linear neural network to approximate stochastic processes
• On explaining the surprising success of reservoir computing forecaster of chaos? The universal machine learning dynamical system with contrast to VAR and DMD
• Reservoir Computing
• A Simple Memristive Circuit for Pattern Classification Based on Reservoir Computing
• Fading memory echo state networks are universal
• Neural kernels for recursive support vector regression as a model for episodic memory
• Title not available (Why is that?)
• A new echo state network with variable memory length
• Echo state queueing networks: a combination of reservoir computing and random neural networks
• Evolving Carbon Nanotube Reservoir Computers
• Re-visiting the echo state property
• Direct adaptive control for nonlinear systems using a TSK fuzzy echo state network based on fractional-order learning algorithm
• The role of feedback in morphological computation with compliant bodies
• A biological gradient descent for prediction through a combination of STDP and homeostatic plasticity
• Synthesis of recurrent neural networks for dynamical system simulation
• Unstructured network topology begets order-based representation by privileged neurons
• A decentralized training algorithm for echo state networks in distributed big data applications
• Numerical computation of partial differential equations by hidden-layer concatenated extreme learning machine
• Testing dynamical system variables for reconstruction
• The copula echo state network
• Time series classification with echo memory networks
• Regularized variational Bayesian learning of echo state networks with delay\&sum readout
• The architecture of dynamic reservoir in the echo state network
• Universal discrete-time reservoir computers with stochastic inputs and linear readouts using non-homogeneous state-affine systems
• Nonlinear memory capacity of parallel time-delay reservoir computers in the processing of multidimensional signals
• Detection of generalized synchronization using echo state networks
• Using machine learning to replicate chaotic attractors and calculate Lyapunov exponents from data
• The self-organized critical multiverse
• Search optimization, funnel topography, and dynamical criticality on the string landscape
• Dimension reduction in recurrent networks by canonicalization
• Symbolic computation using cellular automata-based hyperdimensional computing
• Predicting critical transitions in multiscale dynamical systems using reservoir computing
• Recurrent kernel machines: computing with infinite echo state networks
• Assessing the robustness of critical behavior in stochastic cellular automata
• Deep learning algorithm for data-driven simulation of noisy dynamical system
• Stochastic nonlinear time series forecasting using time-delay reservoir computers: performance and universality
• Synchronization of reservoir computers with applications to communications
• Modeling chaotic systems: dynamical equations vs machine learning approach
• Internal dynamics of recurrent neural networks trained to generate complex spatiotemporal patterns
• Constraining chaos: enforcing dynamical invariants in the training of reservoir computers
• Stochastic facilitation in heteroclinic communication channels
• Learning continuous chaotic attractors with a reservoir computer
• Robust forecasting using predictive generalized synchronization in reservoir computing
• Dynamics of spiking map-based neural networks in problems of supervised learning
• Real-time sensory-motor integration of hippocampal place cell replay and prefrontal sequence learning in simulated and physical rat robots for novel path optimization
• Comparison of deep neural networks and deep hierarchical models for spatio-temporal data
• FREEMAN'S K MODELS AS RESERVOIR COMPUTING ARCHITECTURES
• Transfer-RLS method and transfer-FORCE learning for simple and fast training of reservoir computing models
• Bayesian framework for simulation of dynamical systems from multidimensional data using recurrent neural network
• Deep echo state networks with uncertainty quantification for spatio-temporal forecasting
• Anticipating measure synchronization in coupled Hamiltonian systems with machine learning
• Time-series forecasting using manifold learning, radial basis function interpolation, and geometric harmonics
• Critical neuromorphic computing based on explosive synchronization
• Large sampling intervals for learning and predicting chaotic systems with reservoir computing
• Collective dynamics of rate neurons for supervised learning in a reservoir computing system
• Transitions in echo index and dependence on input repetitions
• Title not available (Why is that?)
• Multifunctionality in a reservoir computer
• Transfer learning of chaotic systems
• Design of a negative group delay filter via reservoir computing approach: real-time prediction of chaotic signals
• Reservoirs learn to learn
• Effective connectivity at synaptic level in humans: a review and future prospects
• DNA reservoir computing: a novel molecular computing approach
• Hybridizing traditional and next-generation reservoir computing to accurately and efficiently forecast dynamical systems
• Model adaptive phase space reconstruction
• The roles of Kerr nonlinearity in a bosonic quantum neural network

Uses Software

• darch
• Evolino

This page was built for publication: Reservoir computing approaches to recurrent neural network training

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q458488)