Search research 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

Search research articles

Related Experiment Videos

Object selection by an oscillatory neural network.

Yakov Kazanovich¹, Roman Borisyuk

¹Centre for Neural and Adaptive Systems, School of Computing, Plymouth University, Drake Circus, Plymouth PL4 8AA, UK. yakovk@soc.plym.ac.uk

|December 3, 2002

Summary

This study introduces a novel oscillatory neural network for consecutive object selection in visual scenes. The network reliably identifies objects using frequency coding and synchronized oscillator principles.

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

Beyond locomotion: How specialized motor patterns enable a vertebrate to struggle free from capture.

iScience·2025

Same author

Graph theory methods for analyzing functional connectivity in multiple spike trains: application to data recorded from the visual cortex of a cat.

Cognitive neurodynamics·2025

Same author

Non-conventional deep brain stimulation in a network model of movement disorders.

Biomedical physics & engineering express·2024

Same author

Mechanisms Underlying the Recruitment of Inhibitory Interneurons in Fictive Swimming in Developing <i>Xenopus laevis</i> Tadpoles.

The Journal of neuroscience : the official journal of the Society for Neuroscience·2023

Same author

From decision to action: Detailed modelling of frog tadpoles reveals neuronal mechanisms of decision-making and reproduces unpredictable swimming movements in response to sensory signals.

PLoS computational biology·2021

Same author

A computational model of familiarity detection for natural pictures, abstract images, and random patterns: Combination of deep learning and anti-Hebbian training.

Neural networks : the official journal of the International Neural Network Society·2021

Area of Science:

Computational Neuroscience
Artificial Intelligence
Computer Vision

Background:

Consecutive object selection in visual scenes is a complex computational challenge.
Existing neural network models often struggle with dynamic object recognition and selection.

Purpose of the Study:

To propose a new oscillatory neural network model for reliable consecutive object selection.
To demonstrate the network's functionality using frequency coding and synchronized oscillations.

Main Methods:

Development of an oscillatory neural network with a central executive oscillator.
Implementation of frequency coding for greyscale image representation.
Utilizing principles of oscillator synchronization, frequency adaptation, and resonant amplitude increase.

Related Experiment Videos

Main Results:

Simulations show reliable consecutive object selection.
The network performs effectively under varying object brightness conditions.
Demonstrated robustness in dynamic visual scene analysis.

Conclusions:

The proposed oscillatory neural network offers a viable solution for consecutive object selection.
The network's design based on synchronization and resonance enhances its performance.
This approach has potential applications in advanced computer vision systems.