Complete controllability of continuous-time recurrent neural networks

DOI10.1016/S0167-6911(97)00002-9zbMath0901.93005OpenAlexW2025779039MaRDI QIDQ1391523

Héctor J. Sussmann, Eduardo D. Sontag

Publication date: 22 July 1998

Published in: Systems \& Control Letters (Search for Journal in Brave)

Full work available at URL: https://doi.org/10.1016/s0167-6911(97)00002-9

zbMATH Keywords

controllabilityneural networksglobal stabilizationlinear discrete-time systemssaturated feedback

Mathematics Subject Classification ID

Controllability (93B05) Neural networks for/in biological studies, artificial life and related topics (92B20)

Related Items (10)

Turnpike in optimal control of PDEs, ResNets, and beyond ⋮ Challenges in optimization with complex PDE-systems. Abstracts from the workshop held February 14--20, 2021 (hybrid meeting) ⋮ Summability characterizations of uniform exponential and asymptotic stability of sets for difference inclusions ⋮ The ISS framework for time-delay systems: a survey ⋮ Neural ODE Control for Classification, Approximation, and Transport ⋮ On the theory of flexible neural networks – Part I: a survey paper ⋮ A non-ellipsoidal reachable set estimation for uncertain neural networks with time-varying delay ⋮ Hybrid online learning control in networked multiagent systems: A survey ⋮ A learning result for continuous-time recurrent neural networks ⋮ Further results on controllability of recurrent neural networks

Cites Work

• Vapnik-Chervonenkis dimension of recurrent neural networks
• State observability in recurrent neural networks
• Using Fourier-neural recurrent networks to fit sequential input/output data
• On the computational power of neural nets
• Forward accessibility for recurrent neural networks
• Sample complexity for learning recurrent perceptron mappings
• Unnamed Item
• Unnamed Item
• Unnamed Item

This page was built for publication: Complete controllability of continuous-time recurrent neural networks