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 function learning by unsupervised neurons.

S Fiori1

  • 1Neural Networks and Adaptive Systems Research Group, Dipartimento di Ingegneria Industriale, Universita' di Perugia, Perugia Italy. sfr@unipg.it

International Journal of Neural Systems
|December 26, 2001
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

PROMPT to improve speech motor abilities in children with cerebral palsy: a wait-list control group trial protocol.

BMC neurology·2022
Same author

LUNCH-Lung Ultrasound for early detection of silent and apparent aspiratioN in infants and young CHildren with cerebral palsy and other developmental disabilities: study protocol of a randomized controlled trial.

BMC pediatrics·2022
Same author

Automating Quantitative Measures of an Established Conventional MRI Scoring System for Preterm-Born Infants Scanned between 29 and 47 Weeks' Postmenstrual Age.

AJNR. American journal of neuroradiology·2021
Same author

Dissection of DLBCL microenvironment provides a gene expression-based predictor of survival applicable to formalin-fixed paraffin-embedded tissue.

Annals of oncology : official journal of the European Society for Medical Oncology·2019
Same author

Dissection of DLBCL microenvironment provides a gene expression-based predictor of survival applicable to formalin-fixed paraffin-embedded tissue.

Annals of oncology : official journal of the European Society for Medical Oncology·2018
Same author

<i>Reply</i>.

AJNR. American journal of neuroradiology·2017
Same journal

Latent Space Projections and Atlases, a Cautionary Tale in Deep Neuroimaging using Autoencoders.

International journal of neural systems·2026
Same journal

Transformer-Based Anomaly Detection for Neurodegenerative Screening in MRI Images.

International journal of neural systems·2026
Same journal

Discrete Wavelet Convolution for Learnable Time-Frequency Representation with Application to Seizure Prediction.

International journal of neural systems·2026
Same journal

Automatic Seizure Detection using Hierarchical Spectral-Temporal Feature Learning with an Imbalance-Aware Transformer.

International journal of neural systems·2026
Same journal

Pyramid Vision Transformer-Enhanced Conformer Network for Epileptic Seizure Recognition Using MultiChannel EEG Signals.

International journal of neural systems·2026
Same journal

A Time-Frequency Decoupled Contrastive Learning Framework for Electroencephalography-Based Parkinson's Disease Diagnosis.

International journal of neural systems·2026
See all related articles

This study explores pseudo-polynomial adaptive activation function neurons (FANs) for unsupervised learning from incomplete data. The research extends FAN theory to asymmetric densities and compares its universal approximation ability with other methods.

Area of Science:

  • Computational Neuroscience
  • Machine Learning
  • Information Theory

Background:

  • Introduced pseudo-polynomial adaptive activation function neuron (FAN).
  • Presented unsupervised information-theoretic learning theory for FANs.
  • Developed a learning model based on entropy optimization for probability distribution learning from incomplete data.

Purpose of the Study:

  • Illustrate theoretical features of the FAN neuron.
  • Extend FAN learning theory to asymmetrical density function approximation.
  • Compare FANs with existing density function estimation methods, focusing on universal approximation ability.

Main Methods:

  • Entropy optimization for unsupervised learning.
  • Information-theoretic learning principles.

Related Experiment Videos

  • Analytical and numerical comparisons with established density estimation techniques.

    • Main Results:

    • Demonstrated theoretical properties of FAN neurons.
    • Extended learning theory for asymmetric density approximation.
    • Provided comparative analysis highlighting FANs' universal approximation capabilities.
    • Surveyed PDF learning from incomplete data.

    Conclusions:

    • FAN neurons offer a robust framework for unsupervised learning from incomplete data.
    • The extended theory supports asymmetrical density approximation.
    • FANs show competitive universal approximation ability compared to other methods.