Parameter Estimation of Sigmoid Superpositions: Dynamical System Approach

Ivan Tyukin, Cees van Leeuwen, Danil V. Prokhorov

NeCo 2003 pp. 2419-2455

doi:10.1162/089976603322362428 /neco/2003/tyukin2003neco-parameter/

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.

PDF NeCo Semantic Scholar

Cite

Text

Tyukin et al. "Parameter Estimation of Sigmoid Superpositions: Dynamical System Approach." Neural Computation, 2003. doi:10.1162/089976603322362428

Markdown

[Tyukin et al. "Parameter Estimation of Sigmoid Superpositions: Dynamical System Approach." Neural Computation, 2003.](https://mlanthology.org/neco/2003/tyukin2003neco-parameter/) doi:10.1162/089976603322362428

BibTeX

@article{tyukin2003neco-parameter,
  title     = {{Parameter Estimation of Sigmoid Superpositions: Dynamical System Approach}},
  author    = {Tyukin, Ivan and van Leeuwen, Cees and Prokhorov, Danil V.},
  journal   = {Neural Computation},
  year      = {2003},
  pages     = {2419-2455},
  doi       = {10.1162/089976603322362428},
  volume    = {15},
  url       = {https://mlanthology.org/neco/2003/tyukin2003neco-parameter/}
}