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

Probability Density Estimation Using Entropy Maximization

Miller1, Horn

  • 1Tel-Aviv University, School of Physics and Astronomy, Tel-Aviv, IL, 69978.

Neural Computation
|September 23, 1998
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

Identification of critical staphylococcal genes using conditional phenotypes generated by antisense RNA.

Science (New York, N.Y.)·2001
Same author

Erratum

International journal of cancer·2000
Same author

Krimmel et al. reply:

Physical review letters·2000
Same author

Differences in alcohol risk profiles between college students and college-age non-students presenting for care in the emergency department.

Annals of epidemiology·2000
Same author

Charge order in NaV2O5 studied by EPR

Physical review letters·2000
Same author

Quasicrystalline valence bands in decagonal AlNiCo

Nature·2000

This study introduces a novel method for estimating probability density functions using entropy maximization and stochastic variables. The approach, implemented with neural networks, enables data generation from learned distributions.

Area of Science:

  • Machine Learning
  • Statistical Modeling
  • Information Theory

Background:

  • Estimating probability density functions is crucial for statistical modeling and machine learning.
  • Existing methods may face challenges with complex, high-dimensional data distributions.

Purpose of the Study:

  • To develop a new algorithm for estimating probability and conditional density functions.
  • To leverage entropy maximization for robust distribution estimation and data generation.

Main Methods:

  • The proposed method utilizes novel stochastic variables for input coding based on entropy maximization.
  • The algorithm integrates encoding for probability estimation and decoding for data generation.
  • Implementation employs neural networks trained via stochastic gradient ascent.

Related Experiment Videos

Main Results:

  • The algorithm provides accurate estimates of probability distributions.
  • The decoding step successfully generates data conforming to the estimated distribution.
  • The method demonstrates a close relationship to the maximum likelihood approach.

Conclusions:

  • The developed algorithm offers an effective approach for density estimation and generative modeling.
  • Its neural network implementation and reliance on entropy maximization provide a powerful tool for data analysis.