Approximating nonlinear fading-memory operators using neural network models

DOI10.1007/BF01189878zbMath0774.93036MaRDI QIDQ1207738

Michael B. Matthews

Publication date: 23 May 1993

Published in: Circuits, Systems, and Signal Processing (Search for Journal in Brave)

zbMATH Keywords

fading-memory systeminfinite-memory system modelsnonlinear finite-memory

Mathematics Subject Classification ID

Learning and adaptive systems in artificial intelligence (68T05) Neural networks for/in biological studies, artificial life and related topics (92B20) Nonlinear systems in control theory (93C10)

Related Items (8)

Metric entropy limits on recurrent neural network learning of linear dynamical systems ⋮ Echo state networks are universal ⋮ Fading memory echo state networks are universal ⋮ Approximation bounds for random neural networks and reservoir systems ⋮ Learning strange attractors with reservoir systems ⋮ Unnamed Item ⋮ Unnamed Item ⋮ Memory and forecasting capacities of nonlinear recurrent networks

Cites Work

• Unnamed Item
• Unnamed Item
• Multilayer feedforward networks are universal approximators
• Fading memory and the problem of approximating nonlinear operators with Volterra series
• Second-order Volterra filtering and its application to nonlinear system identification
• Analysis of recursive stochastic algorithms
• Approximation by superpositions of a sigmoidal function

This page was built for publication: Approximating nonlinear fading-memory operators using neural network models