Search research articles

Search research articles

Related Experiment Videos

Self-organizing neural projections.

Teuvo Kohonen¹

¹Helsinki University of Technology, Neural Networks Research Centre, P.O. Box 5400, FI-02015 HUT, Finland. teuvo.kohonen@hut.fi

Neural Networks : the Official Journal of the International Neural Network Society

|June 16, 2006

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

Essentials of the self-organizing map.

Neural networks : the official journal of the International Neural Network Society·2012

Same author

Contextual self-organizing map: software for constructing semantic representations.

Behavior research methods·2011

Same author

How to make large self-organizing maps for nonvectorial data.

Neural networks : the official journal of the International Neural Network Society·2002

Same author

Modeling of automatic capture and focusing of visual attention.

Proceedings of the National Academy of Sciences of the United States of America·2002

Same journal

Anchor-based disentanglement framework for incremental multi-view clustering.

Neural networks : the official journal of the International Neural Network Society·2026

Same journal

Complex-valued amplitude-phase interference modeling for adversarially robust classification.

Neural networks : the official journal of the International Neural Network Society·2026

Same journal

TraNce: Type-aware hypergraph neural network with biological mediators for drug repositioning.

Neural networks : the official journal of the International Neural Network Society·2026

Same journal

Decentralized ADMM for factorization-based Low-rank matrix estimation.

Neural networks : the official journal of the International Neural Network Society·2026

Same journal

Memristive neuromorphic circuit design inspired by the neural mechanisms of conditioned fear.

Neural networks : the official journal of the International Neural Network Society·2026

Same journal

Q-learning based asynchronous Boolean control networks stabilization with data loss.

Neural networks : the official journal of the International Neural Network Society·2026

See all related articles

ABOUT JoVE

Overview Leadership Blog JoVE Help Center

AUTHORS

Publishing Process Editorial Board Scope & Policies Peer Review FAQ Submit

LIBRARIANS

Testimonials Subscriptions Access Resources Library Advisory Board FAQ

RESEARCH

JoVE Journal Methods Collections JoVE Encyclopedia of Experiments Archive

EDUCATION

JoVE Core JoVE Business JoVE Science Education JoVE Lab Manual Faculty Resource Center Faculty Site

Terms & Conditions of Use

A new self-organizing system models neural feature map formation, overcoming limitations of the original Self-Organizing Map (SOM) algorithm. This model enables linear pattern transfer for accurate neural projection mapping.

Area of Science:

Computational Neuroscience
Artificial Intelligence
Machine Learning

Background:

The Self-Organizing Map (SOM) is a data-mining tool used for abstract feature map creation.
SOM principles have been proposed to explain brain feature map formation.
Original SOM has limitations in modeling pointwise neural projections due to its winner-take-all function.

Purpose of the Study:

To introduce a novel self-organizing system model.
To address the limitations of the traditional SOM algorithm for neural projection modeling.
To create a model capable of linear pattern transfer for complex stimuli.

Main Methods:

Developed a new self-organizing system related to the SOM.
Implemented a linear transfer function for patterns and their combinations.

Related Experiment Videos

Utilized randomly interconnected neural layers and random pattern mixtures for training.

Main Results:

The new model successfully creates a pointwise-ordered projection from the input to the output layer.
It demonstrates the ability to transfer signal patterns and handle superimposed stimulus patterns linearly.
When trained with feature detectors, the output layer forms a precise feature map of the inputs.

Conclusions:

The proposed self-organizing system model accurately represents pointwise neural projections.
It overcomes the limitations of the SOM, offering a more suitable model for somatotopic and visual field maps.
This model provides a new framework for understanding feature map formation in biological and artificial systems.