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 Videos

A connectionist model for category perception: theory and implementation.

J Basak1, C A Murthy, S Chaudhury

  • 1Nat. Center for Knowledge Based Comput. Electron., Indian Stat. Inst., Calcutta.

IEEE Transactions on Neural Networks
|January 1, 1993
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

Internal protein motion in a rough model potential.

The Journal of chemical physics·2025
Same author

The role of microenvironmental pH regulation on colorectal cancer cells - a preliminary study.

Journal of physiology and pharmacology : an official journal of the Polish Physiological Society·2025
Same author

The novel estrogen receptor beta agonist EGX358 and <i>APOE</i> genotype influence memory, vasomotor, and anxiety outcomes in an Alzheimer's mouse model.

Frontiers in aging neuroscience·2024
Same author

Deciphering miRNA-lncRNA-mRNA interaction through experimental validation of miRNAs, lncRNAs, and miRNA targets on mRNAs in Cajanus cajan.

Plant biology (Stuttgart, Germany)·2024
Same author

The dynamics of violence in everyday living - an Indian context.

The International journal of psycho-analysis·2023
Same author

Concerns about the future linked with poor sleep quality in US army special operations soldiers withdrawing from Afghanistan.

BMJ military health·2022
Same journal

Universal perceptron and DNA-like learning algorithm for binary neural networks: LSBF and PBF implementations.

IEEE transactions on neural networks·2013
Same journal

Guest editorial: special section on white box nonlinear prediction models.

IEEE transactions on neural networks·2011
Same journal

Data-based fault-tolerant control of high-speed trains with traction/braking notch nonlinearities and actuator failures.

IEEE transactions on neural networks·2011
Same journal

Guest editorial: special section on data-based control, modeling, and optimization.

IEEE transactions on neural networks·2011
Same journal

Neural network-based multiple robot simultaneous localization and mapping.

IEEE transactions on neural networks·2011
Same journal

Data-driven model-free adaptive control for a class of MIMO nonlinear discrete-time systems.

IEEE transactions on neural networks·2011
See all related articles

This study introduces a connectionist model for object recognition. The system effectively identifies multiple overlapping objects using confidence values and probabilistic learning, even when occluded.

Area of Science:

  • Computer Science
  • Artificial Intelligence
  • Machine Learning

Background:

  • Object recognition is a fundamental challenge in computer vision.
  • Existing models often struggle with simultaneous recognition of multiple, overlapping objects.

Purpose of the Study:

  • To present a novel connectionist model for learning and recognizing object classes.
  • To enable simultaneous recognition of multiple objects, even when occluded.

Main Methods:

  • Developed a network utilizing confidence values for feature presence.
  • Defined and minimized an error function for optimal object class determination.
  • Employed probabilistic measures for the learning theory in supervised mode.

Main Results:

Related Experiment Videos

  • The model successfully recognizes multiple objects simultaneously with overlapped features.
  • Demonstrated capability in learning individual objects via supervised learning.
  • Experimental results validate the model's performance.

Conclusions:

  • The proposed connectionist model offers a robust solution for multi-object recognition.
  • The model effectively handles occluded objects, advancing object detection capabilities.