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 Concept Videos

Neural Circuits01:25

Neural Circuits

Neural circuits and neuronal pools are two of the main structures found in the nervous system. Neural circuits are networks of neurons that work together to carry out a specific task or process. They consist of interconnected neurons and glial cells, which provide structural and metabolic support.
Neuronal pools are collections of nerve cells with similar functions and interact through chemical and electrical signals. These pools include both interneurons (the central neural circuit nodes that...
Area Between Curves: Problem Solving01:27

Area Between Curves: Problem Solving

A region can be enclosed by three curves: a square root function, a reflected cube root function, and a linear function. The linear function intersects each of the other two curves, and these intersection points determine where the boundary of the enclosed region changes. Because different curves serve as the upper and lower boundaries in different parts of the graph, the area cannot be found using a single setup over the entire interval.To compute the area, the region is first divided into two...
Reducing Line Loss01:18

Reducing Line Loss

In a three-phase circuit, line loss is an indicator of energy dissipated as heat due to the resistance of transmission lines. To address this, incorporating transformers into the system—a step-up transformer at the source and a step-down transformer at the load—is a strategic solution. Two three-phase transformers are introduced to improve this.
With a step-up transformer at the source, the voltage is increased, thereby reducing the current in the transmission lines since power loss in...
Uniform Depth Channel Flow: Problem Solving01:18

Uniform Depth Channel Flow: Problem Solving

To calculate the flow rate for a trapezoidal channel, first, identify the bottom width, side slope, and flow depth of the channel. The cross-sectional area (A) corresponding to the depth of flow (y), channel bottom width (B), and side slope (θ) is determined by:Next, calculate the wetted perimeter, which includes the bottom width and the sloped side lengths in contact with the water. Using the values of the cross-sectional area and the wetted perimeter, determine the hydraulic radius by...
Sequence Networks of Rotating Machines01:24

Sequence Networks of Rotating Machines

A Y-connected synchronous generator, grounded through a neutral impedance, is designed to produce balanced internal phase voltages with only positive-sequence components. The generator's sequence networks include a source voltage that is exclusively in the positive-sequence network. The sequence components of line-to-ground voltages at the generator terminals illustrate this configuration.
Zero-sequence current induces a voltage drop across the generator's neutral impedance and other...
Level Curves and Contour Maps01:22

Level Curves and Contour Maps

Level curves and contour maps provide a way to visualize functions of two variables on a two-dimensional plane. A useful example is a topographic map, where curved lines represent locations that share the same elevation. In mathematics, these curves are called level curves or contour lines. Each contour line corresponds to points in the domain where the function has a constant value. For a function of two variables written as z = f(x,y), a level curve is defined by the equation f(x,y) = k,...

You might also read

Related Articles

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

Sort by
Same author

Efficient IntVec: High recognition rate with reduced computational cost.

Neural networks : the official journal of the International Neural Network Society·2019
Same author

Introduction.

International journal of neural systems·2018
Same author

Margined winner-take-all: New learning rule for pattern recognition.

Neural networks : the official journal of the International Neural Network Society·2017
Same author

Training multi-layered neural network neocognitron.

Neural networks : the official journal of the International Neural Network Society·2013
Same author

Artificial vision by multi-layered neural networks: neocognitron and its advances.

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

Increasing robustness against background noise: visual pattern recognition by a neocognitron.

Neural networks : the official journal of the International Neural Network Society·2011
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
Same journal

New results on prescribed-time synchronization of complex networks via intermittent control.

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

Variance-constrained multi-view ensemble broad network for imbalanced data.

Neural networks : the official journal of the International Neural Network Society·2026
See all related articles

Related Experiment Video

Updated: Jun 19, 2026

End-To-End Deep Neural Network for Salient Object Detection in Complex Environments
03:31

End-To-End Deep Neural Network for Salient Object Detection in Complex Environments

Published on: December 15, 2023

Neural network model for completing occluded contours.

Kunihiko Fukushima1

  • 1Kansai University, Takatsuki, Osaka, Japan. fukushima@m.ieice.org

Neural Networks : the Official Journal of the International Neural Network Society
|October 30, 2009
PubMed
Summary
This summary is machine-generated.

This study introduces a neural network model for amodal completion, enabling the visual system to infer occluded shapes from visible contours. The model mimics human perception by predicting missing pattern parts using hierarchical processing.

More Related Videos

Application of Deep Learning-Based Medical Image Segmentation via Orbital Computed Tomography
04:48

Application of Deep Learning-Based Medical Image Segmentation via Orbital Computed Tomography

Published on: November 30, 2022

Related Experiment Videos

Last Updated: Jun 19, 2026

End-To-End Deep Neural Network for Salient Object Detection in Complex Environments
03:31

End-To-End Deep Neural Network for Salient Object Detection in Complex Environments

Published on: December 15, 2023

Application of Deep Learning-Based Medical Image Segmentation via Orbital Computed Tomography
04:48

Application of Deep Learning-Based Medical Image Segmentation via Orbital Computed Tomography

Published on: November 30, 2022

Area of Science:

  • Computational neuroscience
  • Computer vision
  • Psychophysics

Background:

  • The human visual system can perceive complete shapes even when parts are occluded.
  • This phenomenon, known as amodal completion, involves inferring unseen contours from visible ones.

Purpose of the Study:

  • To propose a novel neural network model that simulates amodal completion.
  • To investigate the computational mechanisms underlying the perception of occluded shapes.

Main Methods:

  • A hierarchical, multi-layered neural network with bottom-up and top-down pathways was developed.
  • The model incorporates simulated cells from visual areas V1 (edge orientation) and V2 (bend angle detection).
  • Bend-extracting cell responses were used to predict occluded contour curvature and location.

Main Results:

  • The neural network model successfully performed amodal completion on various visual stimuli.
  • Simulated extrapolation and interpolation of missing contours from visible parts were demonstrated.
  • Model performance showed similarity to results from psychological experiments on amodal completion.

Conclusions:

  • The proposed neural network model effectively replicates amodal completion, a key aspect of visual perception.
  • Hierarchical processing of contour and bend information is crucial for inferring occluded shapes.
  • This model provides a computational framework for understanding how the brain completes visual patterns.