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

String tightening as a self-organizing phenomenon.

Bonny Banerjee1

  • 1Laboratory for AI Research, Department of Computer Science and Engineering, The Ohio State University, Columbus, OH 43210, USA. banerjee@cse.ohio-state.edu

IEEE Transactions on Neural Networks
|January 29, 2008
PubMed
Summary
This summary is machine-generated.

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

Correction: Current paradigm and futuristic vision on new-onset diabetes and pancreatic cancer research.

Frontiers in pharmacology·2025
Same author

Current paradigm and futuristic vision on new-onset diabetes and pancreatic cancer research.

Frontiers in pharmacology·2025
Same author

Attention-Based Variational Autoencoder Models for Human-Human Interaction Recognition via Generation.

Sensors (Basel, Switzerland)·2024
Same author

AttentionMNIST: a mouse-click attention tracking dataset for handwritten numeral and alphabet recognition.

Scientific reports·2023
Same author

Pragmatically Framed Cross-Situational Noun Learning Using Computational Reinforcement Models.

Frontiers in psychology·2018
Same author

Corpus of deaf speech for acoustic and speech production research.

The Journal of the Acoustical Society of America·2017
Same journal

Universal perceptron and DNA-like learning algorithm for binary neural networks: LSBF and PBF implementations.

IEEE transactions on neural networks·2013
Same journal

Guest editorial: special section on white box nonlinear prediction models.

IEEE transactions on neural networks·2011
Same journal

Data-based fault-tolerant control of high-speed trains with traction/braking notch nonlinearities and actuator failures.

IEEE transactions on neural networks·2011
Same journal

Guest editorial: special section on data-based control, modeling, and optimization.

IEEE transactions on neural networks·2011
Same journal

Neural network-based multiple robot simultaneous localization and mapping.

IEEE transactions on neural networks·2011
Same journal

Data-driven model-free adaptive control for a class of MIMO nonlinear discrete-time systems.

IEEE transactions on neural networks·2011
See all related articles

A novel neural network, the string tightening self-organizing neural network (STON), models self-organization for pathfinding. This anytime algorithm finds shortest paths by mimicking a tightening string, useful in robotics and AI.

Area of Science:

  • Artificial Intelligence
  • Computational Geometry
  • Robotics

Background:

  • Self-organization is a key phenomenon in neural networks.
  • Existing self-organizing maps (SOMs) have limitations in modeling physical self-organization processes.
  • Modeling the tightening of a string offers a novel approach to self-organization.

Purpose of the Study:

  • Introduce a new neural network model, the string tightening self-organizing neural network (STON).
  • Demonstrate STON's capability to solve practical problems like shortest path computation and path smoothing.
  • Provide a method for finding the shortest Euclidean path in the presence of obstacles.

Main Methods:

  • Develop a variant of the self-organizing map (SOM) inspired by string tightening.

Related Experiment Videos

  • Implement the STON model to dynamically create and select feature vectors competitively.
  • Utilize an anytime algorithm approach for continuous convergence to the shortest path.

    • Main Results:

    • The STON model successfully models the self-organization of particles in a tightening string.
    • The algorithm converges to the unique shortest path configuration in Euclidean space.
    • Experimental results validate the correctness and effectiveness of the STON model.

    Conclusions:

    • The STON model offers an effective solution for shortest path computation and related geometric problems.
    • This approach has broad applications in robotics, AI, VLSI routing, and geographical information systems.
    • The STON provides a novel perspective on self-organization within neural networks.