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

Vector Algebra: Method of Components01:08

Vector Algebra: Method of Components

It is cumbersome to find the magnitudes of vectors using the parallelogram rule or using the graphical method to perform mathematical operations like addition, subtraction, and multiplication. There are two ways to circumvent this algebraic complexity. One way is to draw the vectors to scale, as in navigation, and read approximate vector lengths and angles (directions) from the graphs. The other way is to use the method of components.
In many applications, the magnitudes and directions of...
Multi-input and Multi-variable systems01:22

Multi-input and Multi-variable systems

Cruise control systems in cars are designed as multi-input systems to maintain a driver's desired speed while compensating for external disturbances such as changes in terrain. The block diagram for a cruise control system typically includes two main inputs: the desired speed set by the driver and any external disturbances, such as the incline of the road. By adjusting the engine throttle, the system maintains the vehicle's speed as close to the desired value as possible.
In the absence of...
Superposition Theorem for AC Circuits01:13

Superposition Theorem for AC Circuits

Consider encountering a circuit in a steady state where all its inputs are sinusoidal, yet they do not all possess the same frequency. Such a circuit is not classified as an alternating current (AC) circuit, and consequently, its currents and voltages will not exhibit sinusoidal behavior. However, this circuit can be analyzed using the principle of superposition.
The principle of superposition stipulates that the output of a linear circuit with several concurrent inputs is equivalent to the...

You might also read

Related Articles

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

Sort by
Same author

The effect of ketamine and D-cycloserine on the high frequency resting EEG spectrum in humans.

Psychopharmacology·2022
Same author

Fitting predictive coding to the neurophysiological data.

Brain research·2019
Same author

A Hierarchical Predictive Coding Model of Object Recognition in Natural Images.

Cognitive computation·2017
Same author

Predictive coding as a model of cognition.

Cognitive processing·2016
Same author

A review of predictive coding algorithms.

Brain and cognition·2016
Same author

Classification using sparse representations: a biologically plausible approach.

Biological cybernetics·2013
Same journal

RETRACTION: Real-Time Modulation of Physical Training Intensity Based on Wavelet Recursive Fuzzy Neural Networks.

Computational intelligence and neuroscience·2026
Same journal

RETRACTION: Multidimensional Heterogeneous Network Link Adaptation Based on Mobile Environment.

Computational intelligence and neuroscience·2026
Same journal

RETRACTION: Framework to Segment and Evaluate Multiple Sclerosis Lesion in MRI Slices Using VGG-UNet.

Computational intelligence and neuroscience·2026
Same journal

RETRACTION: Facial Emotion Recognition Using a Novel Fusion of Convolutional Neural Network and Local Binary Pattern in Crime Investigation.

Computational intelligence and neuroscience·2026
Same journal

RETRACTION: Automatic Intelligent System Using Medical of Things for Multiple Sclerosis Detection.

Computational intelligence and neuroscience·2026
Same journal

RETRACTION: Intangible Cultural Heritage Reproduction and Revitalization: Value Feedback, Practice, and Exploration Based on the IPA Model.

Computational intelligence and neuroscience·2026
See all related articles

Related Experiment Videos

Unsupervised learning of overlapping image components using divisive input modulation.

M W Spratling1, K De Meyer, R Kompass

  • 1Division of Engineering, King's College London, London WC2R 2LS, UK. michael.spratling@kcl.ac.uk

Computational Intelligence and Neuroscience
|May 9, 2009
PubMed
Summary
This summary is machine-generated.

We introduce Divisive Input Modulation (DIM), a novel unsupervised learning algorithm inspired by neural networks. DIM efficiently learns image components, even with significant overlap and occlusion, outperforming previous methods.

Related Experiment Videos

Area of Science:

  • Computational Neuroscience
  • Machine Learning
  • Image Processing

Background:

  • Nonnegative matrix factorization (NMF) shares mathematical links with competitive neural networks using negative feedback.
  • Existing methods struggle with significant overlap and occlusion in image component learning.

Purpose of the Study:

  • To introduce Divisive Input Modulation (DIM), a novel, computationally efficient unsupervised learning algorithm.
  • To evaluate DIM's performance in learning image components, particularly with overlapping features.
  • To compare DIM against state-of-the-art algorithms on a challenging artificial image parsing task.

Main Methods:

  • Developed the Divisive Input Modulation (DIM) algorithm, inspired by NMF and negative feedback neural networks.
  • Created a novel artificial task using overlapping squares to assess component parsing and learning.
  • Compared DIM's performance against established algorithms on the artificial task, focusing on overlap and occlusion handling.

Main Results:

  • DIM demonstrates mathematical simplicity and computational efficiency for unsupervised learning of image components.
  • The algorithm successfully parses artificial images with overlapping features.
  • DIM effectively learns elementary components from training images, even with considerable overlap.
  • DIM outperforms predecessors in handling overlap and occlusion on the novel task.

Conclusions:

  • Divisive Input Modulation (DIM) offers a robust and efficient solution for unsupervised image component learning.
  • The algorithm's ability to manage feature overlap and occlusion represents a significant advancement.
  • DIM shows promise for applications requiring the decomposition of complex, overlapping visual information.