Parameter Estimation of Sigmoid Superpositions: Dynamical System Approach

DOI10.1162/089976603322362428zbMath1085.68653arXivmath/0207075OpenAlexW2137571295WikidataQ35544472 ScholiaQ35544472MaRDI QIDQ4461330

Danil Prokhorov, Cees van Leeuwen, I. Yu. Tyukin

Publication date: 30 March 2004

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

Full work available at URL: https://arxiv.org/abs/math/0207075

Mathematics Subject Classification ID

Learning and adaptive systems in artificial intelligence (68T05)

Related Items

Knowledge-informed neuro-integrators for aggregation kinetics ⋮ Free energy, value, and attractors

Cites Work

• Optimization by Simulated Annealing
• Parameter identification for uncertain plants using \(H^ \infty\) methods
• Absolute stability of global pattern formation and parallel memory storage by competitive neural networks
• Adaptive observers for single output nonlinear systems
• Stable adaptive observers for nonlinear time-varying systems
• A new adaptive learning rule
• Adaptive observers with exponential rate of convergence
• Universal approximation bounds for superpositions of a sigmoidal function
• Degree of Approximation Results for Feedforward Networks Approximating Unknown Mappings and Their Derivatives
• The unreasonable effectiveness of neural network approximation
• A Global Optimum Approach for One-Layer Neural Networks
• Parameter identification for uncertain linear systems with partial state measurements under an H/sup ∞/ criterion
• Adaptive observers with arbitrary exponential rate of convergence for nonlinear systems
• On continuous-time parameter identification by using observers
• Global adaptive output-feedback control of nonlinear systems. I. Linear parameterization
• Approximation by superpositions of a sigmoidal function