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

Density codes and shape spaces.

Pierre Courrieu1

  • 1Laboratoire de Psychologie Cognitive, CNRS - UMR 6146, Université de Provence, Centre St Charles, Bat. 9, Case D, 3 Place Victor Hugo, 13331 Marseille Cedex 1, France. courrieu@up.univ-mrs.fr

Neural Networks : the Official Journal of the International Neural Network Society
|February 18, 2006
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

Spelling performance on the web and in the lab.

PloS one·2019
Same author

The primacy order effect in complex decision making.

Psychological research·2019
Same author

Brain correlates of phonological recoding of visual symbols.

NeuroImage·2016
Same author

The time course of visual influences in letter recognition.

Cognitive, affective & behavioral neuroscience·2016
Same author

General or idiosyncratic item effects: What is the good target for models?

Journal of experimental psychology. Learning, memory, and cognition·2015
Same author

The unbearable articulatory nature of naming: on the reliability of word naming responses at the item level.

Psychonomic bulletin & review·2012
Same journal

Exploiting audio-visual modalities in videos: Object detection via multi-stage bilateral coupling network.

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

Reliability-aware modality completion with cross-modal distillation for federated learning with missing modalities.

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

IGFD-Net: Illumination-guided frequency decoupling for polarization image fusion.

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

Multiple-Strategies dung beetle optimizer and its applications in engineering optimization and bankruptcy prediction.

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

Aggregating global-scale pixel-wise forgery cues within a graph.

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

Finite-Time intermittent control for secure synchronization of Neutral-Type stochastic delayed neural networks under aperiodic DoS attacks.

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

This study introduces an algorithm to encode probability density functions using point sequences. This enables efficient comparison of functions and invariant shape recognition for neural networks.

Area of Science:

  • Computational geometry
  • Machine learning
  • Data analysis

Background:

  • Probability density functions (PDFs) are crucial for representing data distributions.
  • Comparing PDFs often requires complex statistical methods.
  • Geometric transformations are common in data analysis, especially in visual recognition.

Purpose of the Study:

  • To develop an algorithm for encoding probability density functions (PDFs) into point sequences.
  • To enable efficient and invariant comparison of different PDFs.
  • To create suitable input spaces for pattern recognition and analysis neural networks.

Main Methods:

  • Encoding probability density functions (PDFs) associated with samples of points in R(n) into a sequence of points.
  • Matching code points from different PDFs for efficient comparison.

Related Experiment Videos

  • Achieving invariance to specific geometrical transformations via triangular Jacobian matrices.

    • Main Results:

    • The algorithm generates a code (sequence of points) whose density approximates the original data's PDF.
    • Code points allow for direct matching and comparison of different PDFs.
    • The comparison method is invariant to a class of geometrical transformations, useful for shape recognition.

    Conclusions:

    • The developed algorithm provides an efficient method for representing and comparing probability density functions (PDFs).
    • The invariance property makes it suitable for building shape spaces for neural network pattern recognition.
    • A parallel neural implementation is available for 2D image data processing.