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

Minimizing binding errors using learned conjunctive features.

B Mel1, J Fiser

  • 1Department of Biomedical Engineering, University of Southern California, Los Angeles, CA 90089, USA.

Neural Computation
|January 15, 2000
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

Computed lifetimes of metastable states of the NO2+ dication.

The Journal of chemical physics·2008
Same author

Theoretical study of the CS2+ dication.

The Journal of chemical physics·2006
Same author

Worrisome histologic alterations following fine-needle aspiration of the parathyroid.

Journal of clinical pathology·2006
Same author

Computed lifetimes of metastable states of CO2+.

The Journal of chemical physics·2006
Same author

Multireference CI calculation of nuclear quadrupole coupling constants of CN+ and CN-: rovibrational dependence.

Spectrochimica acta. Part A, Molecular and biomolecular spectroscopy·2002
Same author

Unsupervised statistical learning of higher-order spatial structures from visual scenes.

Psychological science·2002
Same journal

A Model-Free Reinforcement Learning Implementation of Decision Making Under Uncertainty by Sequential Sampling.

Neural computation·2026
Same journal

DROP: Distributional and Regular Optimism and Pessimism for Reinforcement Learning.

Neural computation·2026
Same journal

Hierarchical Active Inference Using Successor Representations.

Neural computation·2026
Same journal

W-Kernel and Its Principal Space for Frequentist Evaluation of Bayesian Estimators.

Neural computation·2026
Same journal

A Hidden Markov Model-Inspired Sequence Classification Method for Hyperdimensional Computing.

Neural computation·2026
Same journal

Sparse Graphical Modeling for Electrophysiological Phase-Based Connectivity Using Circular Statistics.

Neural computation·2026
See all related articles

This study models visual recognition, showing how feature complexity and scene clutter affect accuracy. A new algorithm learns compact representations to improve object identification in complex environments.

Area of Science:

  • Computer Vision
  • Cognitive Science
  • Machine Learning

Background:

  • Visual recognition systems face challenges with false positives, known as Malsburg's binding problem.
  • Understanding design trade-offs in spatially invariant conjunctive feature detectors is crucial for robust object recognition.

Purpose of the Study:

  • To develop an analytical model for visual recognition performance.
  • To investigate the impact of object distinguishability, feature count, object complexity, and clutter on recognition accuracy.
  • To introduce a novel feature learning algorithm for creating efficient visual representations.

Main Methods:

  • Derived an analytical model to predict recognition performance based on scene parameters.
  • Used text recognition in cluttered scenes as a simulation domain.

Related Experiment Videos

  • Developed a greedy algorithm for feature learning based on the analytical model.

    • Main Results:

    • The analytical model accurately predicted recognition rates across various clutter loads and feature configurations.
    • The greedy algorithm produced compact, decorrelated feature representations.
    • Learned representations favored features of low conjunctive order for distinguishing objects.

    Conclusions:

    • Spatially invariant conjunctive features can support unambiguous perception in multi-object scenes under specific conditions.
    • The study provides a quantitative framework for understanding visual representation optimization.
    • Insights gained can inform the design of more effective object recognition systems.