Training spatially homogeneous fully recurrent neural networks in eigenvalue space.

DOI10.1016/S0893-6080(96)00079-2zbMath1067.68589OpenAlexW1997442072WikidataQ52196857 ScholiaQ52196857MaRDI QIDQ676596

Renzo Perfetti, Emanuele Massarelli

Publication date: 7 August 1997

Published in: Neural Networks (Search for Journal in Brave)

Full work available at URL: https://doi.org/10.1016/s0893-6080(96)00079-2

zbMATH Keywords

Recurrent neural networksGlobal asymptotic stabilityDiscrete Fourier transformFeature extractionEigenvalue spaceLearning algorithmSpatial homogeneity

Mathematics Subject Classification ID

Learning and adaptive systems in artificial intelligence (68T05)

Related Items (4)

Neural-network-based approach for extracting eigenvectors and eigenvalues of real normal matrices and some extension to real matrices ⋮ A concise functional neural network computing the largest modulus eigenvalues and their corresponding eigenvectors of a real skew matrix ⋮ A recurrent neural network computing the largest imaginary or real part of eigenvalues of real matrices ⋮ A functional neural network computing some eigenvalues and eigenvectors of a special real matrix

Cites Work

• Unnamed Item
• Unnamed Item
• Unnamed Item
• Application of adjoint operators to neural learning
• Dynamics and architecture for neural computation
• Cellular neural networks: theory
• Cellular neural networks: Theory and circuit design
• Sparsely interconnected neural networks for associative memories with applications to cellular neural networks
• Robust Stability and Diagonal Liapunov Functions
• The Relaxation Method for Linear Inequalities

This page was built for publication: Training spatially homogeneous fully recurrent neural networks in eigenvalue space.