Dynamical systems as temporal feature spaces

MaRDI QIDQ4969088zbMATH OpenFDO

Authors Peter Tino

Publication date 5 October 2020

Full work available at URL https://arxiv.org/abs/1907.06382, https://jmlr.csail.mit.edu/papers/v21/19-589.html

zbMATH Keywords

dynamical systemsecho-state networkkernel machinesrecurrent neural networktime series

Mathematics Subject Classification ID

Time series analysis of dynamical systems (37M10) Neural nets and related approaches to inference from stochastic processes (62M45) Learning and adaptive systems in artificial intelligence (68T05)

Recommendations

• Recurrent kernel machines: computing with infinite echo state networks
• The architecture of dynamic reservoir in the echo state network
• Echo state networks are universal
• Embedding and approximation theorems for echo state networks
• Echo state networks with filter neurons and a delay\&sum readout

Cites work

• An introduction to transfer entropy. Information flow in complex systems
• Analog computation via neural networks
• Analysis and Design of Echo State Networks
• Architectural Bias in Recurrent Neural Networks: Fractal Analysis
• Decoupled echo state networks with lateral inhibition
• Design strategies for weight matrices of echo state networks
• Echo state networks are universal
• Echo state networks with filter neurons and a delay\&sum readout
• Echo state property linked to an input: exploring a fundamental characteristic of recurrent neural networks
• Gated Orthogonal Recurrent Units: On Learning to Forget
• scientific article; zbMATH DE number 193132 (Why is no real title available?)
• Learning grammatical structure with Echo State Networks
• Non-asymptotic theory of random matrices: extreme singular values
• Nonlinear memory capacity of parallel time-delay reservoir computers in the processing of multidimensional signals
• Online reservoir adaptation by intrinsic plasticity for backpropagation-decorrelation and echo state learning
• Optimization and applications of echo state networks with leaky- integrator neurons
• Predicting the future of discrete sequences from fractal representations of the past
• Re-visiting the echo state property
• Real-Time Computation at the Edge of Chaos in Recurrent Neural Networks
• Real-Time Computing Without Stable States: A New Framework for Neural Computation Based on Perturbations
• Recurrent Neural Networks with Small Weights Implement Definite Memory Machines
• Reservoir computing approaches to recurrent neural network training
• Statistical Inference for Probabilistic Functions of Finite State Markov Chains
• The asymptotic performance of linear echo state neural networks
• Universal discrete-time reservoir computers with stochastic inputs and linear readouts using non-homogeneous state-affine systems

Cited in

(9)

• Memory and forecasting capacities of nonlinear recurrent networks
• An associative memory readout for ESNs with applications to dynamical pattern recognition
• Recurrent kernel machines: computing with infinite echo state networks
• Predicting critical transitions in multiscale dynamical systems using reservoir computing
• Understanding recurrent neural networks using nonequilibrium response theory
• scientific article; zbMATH DE number 7070561 (Why is no real title available?)
• Learn to synchronize, synchronize to learn
• Reducing echo state network size with controllability matrices
• Linear simple cycle reservoirs at the edge of stability perform Fourier decomposition of the input driving signals

This page was built for publication: Dynamical systems as temporal feature spaces

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q4969088)