Parameter Estimation of Sigmoid Superpositions: Dynamical System Approach
Optimization and Control
2016-09-07 v2 Dynamical Systems
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. Strategies shown in earlier studies to facilitate learning such as randomization of a learning sequence and adding specially designed disturbances during the learning phase are requirements for guaranteeing convergence in the learning scheme proposed.
Cite
@article{arxiv.math/0207075,
title = {Parameter Estimation of Sigmoid Superpositions: Dynamical System Approach},
author = {Ivan Tyukin and Cees van Leeuwen and Danil Prokhorov},
journal= {arXiv preprint arXiv:math/0207075},
year = {2016}
}
Comments
30 pages, 7 figures