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 Video

Updated: Jul 7, 2026

Automated Joint Space Detection Improves Bone Segmentation Accuracy
06:45

Automated Joint Space Detection Improves Bone Segmentation Accuracy

Published on: November 28, 2025

Unsupervised segmentation with dynamical units.

A Ravishankar Rao1, Guillermo A Cecchi, Charles C Peck

  • 1T.J Watson IBM Research Center, Yorktown Heights, NY 10598, USA. ravirao@us.ibm.com

IEEE Transactions on Neural Networks
|February 14, 2008
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

Predicting transition to psychiatric disorders in clinical high-risk for psychosis subjects using machine learning and facial features.

Schizophrenia research·2026
Same author

Abnormal speech production in veterans with bipolar disorder: Relationship to the arcuate fasciculus.

Journal of affective disorders·2026
Same author

Alzheimer's Disease Brain Phenotypes are Age-dependent.

bioRxiv : the preprint server for biology·2026
Same author

Collecting language, speech acoustics, and facial expression to predict psychosis and other clinical outcomes: strategies from the AMP® SCZ initiative.

Schizophrenia (Heidelberg, Germany)·2025
Same author

Incidence, Prevalence, and Stability of Remission in Individuals With Clinical High Risk for Psychosis.

JAMA network open·2025
Same author

The inventory of psychotic-like anomalous self-experiences (IPASE): Stability and relationships with attenuated psychotic symptoms and remission in individuals at-risk for psychosis.

Schizophrenia research·2025

This study introduces a novel unsupervised network for separating learned input mixtures. The network effectively segments input components contributing to classification using amplitude-phase units and Hebbian learning, offering a biologically plausible solution.

Area of Science:

  • Computational Neuroscience
  • Machine Learning
  • Signal Processing

Background:

  • Separating mixed signals is crucial in various fields.
  • Existing methods may struggle with overlapping inputs.
  • Understanding how the brain binds features is a key challenge.

Purpose of the Study:

  • To present a novel network for unsupervised separation of learned input mixtures.
  • To enable segmentation of input components contributing to classification.
  • To offer a biologically plausible model for the binding problem.

Main Methods:

  • Developed a network with amplitude-phase units capable of dynamic synchronization.
  • Employed unsupervised learning based on Hebbian updates.
  • Derived network dynamics from an objective function rewarding sparse coding.

More Related Videos

Deep Learning-Based Segmentation of Cryo-Electron Tomograms
10:25

Deep Learning-Based Segmentation of Cryo-Electron Tomograms

Published on: November 11, 2022

Related Experiment Videos

Last Updated: Jul 7, 2026

Automated Joint Space Detection Improves Bone Segmentation Accuracy
06:45

Automated Joint Space Detection Improves Bone Segmentation Accuracy

Published on: November 28, 2025

Deep Learning-Based Segmentation of Cryo-Electron Tomograms
10:25

Deep Learning-Based Segmentation of Cryo-Electron Tomograms

Published on: November 11, 2022

Main Results:

  • The network successfully separates mixtures of previously learned inputs.
  • It segments components contributing to classification based on phase similarity.
  • Efficient segmentation is achieved even with significant input superposition.

Conclusions:

  • The proposed network offers an effective and simple solution for input separation and component segmentation.
  • The amplitude-phase dynamics provide a potential formal interpretation of the neural binding problem.
  • The network's architecture and dynamics are biologically plausible, suggesting potential neural correlates.