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

Yet another algorithm which can generate topography map.

J Sum1, C S Leung, L W Chan

  • 1Dept. of Comput. Sci. and Eng., Chinese Univ. of Hong Kong, Shatin.

IEEE Transactions on Neural Networks
|January 1, 1997
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

The incidence of arthrogenic muscle inhibition in acute knee injuries: a prospective cohort study in a tertiary acute knee unit.

Asia-Pacific journal of sports medicine, arthroscopy, rehabilitation and technology·2025
Same author

Time Pattern of Presentation of Victims of High-Speed Passenger Ferry Mass Casualty Incidents to the Emergency Department.

Disaster medicine and public health preparedness·2024
Same author

Prenatal diagnosis of pathogenic genomic imbalance in fetuses with increased nuchal translucency but normal karyotyping using chromosomal microarray.

Hong Kong medical journal = Xianggang yi xue za zhi·2019
Same author

Ambulance use affects timely emergency treatment of acute ischaemic stroke.

Hong Kong medical journal = Xianggang yi xue za zhi·2018
Same author

Factors affecting periodontal disease referral and the adherence to guidelines among general dentists.

Australian dental journal·2018
Same author

Clinical and biochemical characteristics of infants with prolonged neonatal jaundice.

Hong Kong medical journal = Xianggang yi xue za zhi·2018
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

This study introduces a novel algorithm for creating topographic maps, similar to self-organizing maps. It utilizes an energy function to enhance neuron correlation, guiding map formation through gradient ascent.

Area of Science:

  • Computational neuroscience
  • Artificial intelligence
  • Machine learning

Background:

  • Self-organizing maps (SOMs) are unsupervised artificial neural networks that produce a low-dimensional (typically two-dimensional) representation of high-dimensional input space.
  • Topographic mapping aims to preserve the relationships between data points in a lower-dimensional space.
  • Existing topographic mapping algorithms may have limitations in capturing local correlations effectively.

Purpose of the Study:

  • To develop a novel algorithm for topographic map formation.
  • To enhance the representation of local correlations between neighboring neurons in a map.
  • To provide an alternative to existing self-organizing map algorithms.

Main Methods:

  • The proposed algorithm defines an energy function that quantifies the local correlation between neighboring neurons.

Related Experiment Videos

  • The algorithm employs a gradient ascent approach on this energy function to iteratively refine the topographic map.
  • Simulations were conducted on two-dimensional maps to evaluate the algorithm's performance.

    • Main Results:

    • The algorithm successfully generates topographic maps that resemble those produced by self-organizing maps.
    • Higher values of the defined energy function indicate stronger local correlations among neighboring neurons.
    • The gradient ascent method effectively optimizes the map based on the energy function.

    Conclusions:

    • The developed algorithm provides an effective method for topographic map formation by leveraging local neuron correlations.
    • The energy function serves as a useful metric for assessing neighborhood relationships in neural maps.
    • This approach offers a promising alternative for unsupervised learning and data visualization tasks.