Memory and forecasting capacities of nonlinear recurrent networks

DOI10.1016/j.physd.2020.132721zbMath1484.68185arXiv2004.11234OpenAlexW3018848489MaRDI QIDQ2116285

Lyudmila Grigoryeva, Juan-Pablo Ortega, Lukas Gonon

Publication date: 16 March 2022

Published in: Physica D (Search for Journal in Brave)

Full work available at URL: https://arxiv.org/abs/2004.11234

zbMATH Keywords

recurrent neural networkmachine learningreservoir computingmemory capacityecho state network (ESN)forecasting capacity

Mathematics Subject Classification ID

Time series, auto-correlation, regression, etc. in statistics (GARCH) (62M10) Learning and adaptive systems in artificial intelligence (68T05) Neural nets and related approaches to inference from stochastic processes (62M45) Networks and circuits as models of computation; circuit complexity (68Q06)

Related Items

Learning strange attractors with reservoir systems ⋮ Dimension reduction in recurrent networks by canonicalization

Cites Work

• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• On some properties of positive definite Toeplitz matrices and their possible applications
• Approximating nonlinear fading-memory operators using neural network models
• Memory in linear recurrent neural networks in continuous time
• Re-visiting the echo state property
• Echo state networks are universal
• Stochastic nonlinear time series forecasting using time-delay reservoir computers: performance and universality
• A local echo state property through the largest Lyapunov exponent
• The Asymptotic Performance of Linear Echo State Neural Networks
• The identification of nonlinear discrete-time fading-memory systems using neural network models
• Echo State Property Linked to an Input: Exploring a Fundamental Characteristic of Recurrent Neural Networks
• Distributed Sequence Memory of Multidimensional Inputs in Recurrent Networks
• Nonlinear Memory Capacity of Parallel Time-Delay Reservoir Computers in the Processing of Multidimensional Signals
• Short-Term Memory Capacity in Networks via the Restricted Isometry Property