Jove
Visualize
Contact Us
JoVE
x logofacebook logolinkedin logoyoutube logo
ABOUT JoVE
OverviewLeadershipBlogJoVE Help Center
AUTHORS
Publishing ProcessEditorial BoardScope & PoliciesPeer ReviewFAQSubmit
LIBRARIANS
TestimonialsSubscriptionsAccessResourcesLibrary Advisory BoardFAQ
RESEARCH
JoVE JournalMethods CollectionsJoVE Encyclopedia of ExperimentsArchive
EDUCATION
JoVE CoreJoVE BusinessJoVE Science EducationJoVE Lab ManualFaculty Resource CenterFaculty Site
Terms & Conditions of Use
Privacy Policy
Policies

Related Experiment Videos

Parameter estimation of sigmoid superpositions: dynamical system approach.

Ivan Tyukin1, Cees van Leeuwen, Danil Prokhorov

  • 1Laboratory for Perceptual Dynamics, RIKEN Brain Science Institute, Wako-shi, Saitama, 351-0198, Japan. tyukinivan@brain.riken.go.jp

Neural Computation
|September 27, 2003
PubMed
Summary

Superposition of sigmoid functions over time is equivalent to solving logistic differential equations. This finding enables effective parameter adjustment procedures with analyzed stability properties.

Related Concept Videos

You might also read

Related Articles

Articles linked to this work by shared authors, journal, and citation graph.

Sort by
Same author

Opening the black box of neural variability: From noise to mechanisms.

Neuroscience and biobehavioral reviews·2026
Same author

The interplay of visual short-term memory, attention, and consciousness: A PRISMA systematic review of behavioral and neuroimaging studies with partial report and change detection.

Neuroscience and biobehavioral reviews·2025
Same author

Perceptual bias in Gestalt grouping by proximity affected by visual working memory load.

Acta psychologica·2025
Same author

Spatiotemporal survival analysis for movement trajectory tracking in virtual reality.

Scientific reports·2025
Same author

Neurocontrol for fixed-length trajectories in environments with soft barriers.

Neural networks : the official journal of the International Neural Network Society·2024
Same author

Machine learning analysis of the effects of COVID-19 on migration patterns.

Scientific reports·2024

Area of Science:

  • Mathematical Modeling
  • Differential Equations
  • Machine Learning Theory

Background:

  • Sigmoid functions are fundamental in various fields, including machine learning and dynamical systems.
  • Understanding their behavior within differential equations is crucial for developing advanced models.

Purpose of the Study:

  • To establish a mathematical equivalence between sigmoid function superposition and logistic differential equations.
  • To develop and analyze an effective parameter adjustment procedure based on this equivalence.

Main Methods:

  • Representing sigmoid function superposition as a linear combination of solutions.
  • Utilizing a linearly parameterized system of logistic differential equations.
  • Analyzing the stability of the proposed parameter adjustment procedure.

Related Experiment Videos

Main Results:

  • Demonstrated the equivalence between sigmoid function superposition and solutions to logistic differential equations.
  • Developed an effective parameter adjustment method leveraging the system's linearity.
  • Provided a stability analysis for the parameter adjustment procedure.

Conclusions:

  • The study provides a novel mathematical framework for analyzing sigmoid functions using logistic differential equations.
  • The proposed parameter adjustment method offers an efficient approach for model calibration.
  • The stability analysis ensures the reliability of the developed procedure.