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

Learning multiple causes by competition enhanced least mean square error reconstruction

B L Zhang1, L Xu, M Fu

  • 1Department of Electrical and Computer Engineering, University of Newcastle, Callaghan, NSW, Australia.

International Journal of Neural Systems
|July 1, 1996
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

Precise Measurement of the Chromoelectric Dipole Moment of the Charm Quark.

Physical review letters·2026
Same author

Precise Measurement of Matter-Antimatter Asymmetry with Entangled Hyperon-Antihyperon Pairs.

Physical review letters·2026
Same author

Observation of Λ[over ¯]p→K^{+}π^{+}π^{-}π^{0} and Λ[over ¯]p→K^{+}π^{+}π^{-}2π^{0}.

Physical review letters·2026
Same author

First Measurement of the D_{s}^{+}→K^{0}μ^{+}ν_{μ} Decay.

Physical review letters·2026
Same author

Observation of the Electromagnetic Radiative Decays of the Λ(1520) and Λ(1690) to γΣ^{0}.

Physical review letters·2026
Same author

Observation of a Threshold Enhancement in the π^{+}π^{-} Spectrum in ψ(3686)→π^{+}π^{-}J/ψ Decays.

Physical review letters·2026
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 introduces a novel self-organization principle for auto-encoder networks, balancing cooperation and competition to achieve a multiple causes model. The proposed anti-Hebbian scheme enhances information processing and simplifies implementation compared to existing methods.

Area of Science:

  • Artificial Intelligence
  • Machine Learning
  • Computational Neuroscience

Background:

  • Recent literature highlights the importance of factorial distributed hidden representations for optimal input reconstruction.
  • Auto-encoder networks are commonly used for representation learning but can suffer from redundancy.

Purpose of the Study:

  • To investigate a self-organization principle for auto-encoders using a factorial distributed hidden representation.
  • To develop a learning scheme that balances cooperation and competition for effective self-organization and multiple causes modeling.

Main Methods:

  • Training an auto-encoder network using Least Mean Square Error Reconstruction (LMSER).
  • Implementing a novel anti-Hebbian scheme with a Receptive Field Overlapping Index (RFOI) penalty to reduce representational redundancy and enhance node competition.

Related Experiment Videos

  • Integrating cooperation and competition for self-organization.

    • Main Results:

    • The proposed learning scheme successfully balances cooperation and competition, enabling the realization of a multiple causes model.
    • Experimental results validate the powerful information processing capabilities of the weighted sum followed by sigmoid activation.
    • The method demonstrates superior ease of implementation and reliability compared to probability theory-based multiple causes models.

    Conclusions:

    • The developed self-organization principle and anti-Hebbian scheme offer an effective approach for representation learning in auto-encoders.
    • This method provides a reliable and simpler alternative for building multiple causes models, accounting for observed data by combining discovered causes or features.