Parameter estimation of sigmoid superpositions: dynamical system approach

Authors:
Ivan Tyukin;Cees van Leeuwen;Danil Prokhorov
Affiliations:
Laboratory for Perceptual Dynamics, RIKEN Brain Science Institute, Wako-shi, Saitama, 351-0198, Japan;Laboratory for Perceptual Dynamics, RIKEN Brain Science Institute, Wako-shi, Saitama, 351-0198, Japan;Ford Research Laboratory, Dearborn, MI
Venue:
Neural Computation
Year:
2003

Citing 11
Cited 0

Realization of robot motion based on a learning method

IEEE Transactions on Systems, Man and Cybernetics
Identifiability of parametric models

Identifiability of parametric models
On the approximate realization of continuous mappings by neural networks

Neural Networks
Universal approximation of an unknown mapping and its derivatives using multilayer feedforward networks

Neural Networks
Approximation and radial-basis-function networks

Neural Computation
Parameter identification for uncertain plants using H∞ methods

Automatica (Journal of IFAC)
System identification and learning control

Iterative learning control
Neural Networks: A Comprehensive Foundation

Neural Networks: A Comprehensive Foundation
A dynamical model for the analysis and acceleration of learning in feedforward networks

Neural Networks
A global optimum approach for one-layer neural networks

Neural Computation
Nonlinear adaptive trajectory tracking using dynamic neural networks

IEEE Transactions on Neural Networks

Quantified Score

Hi-index	0.00

Visualization

Abstract

Superposition of sigmoid function over a finite time interval is shown to be equivalent to the linear combination of the solutions of a linearly parameterized system of logistic differential equations. Due to the linearity with respect to the parameters of the system, it is possible to design an effective procedure for parameter adjustment. Stability properties of this procedure are analyzed.