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

Supervised adaptive Hamming net for classification of multiple-valued patterns

C A Hung1, S F Lin

  • 1Department of Control Engineering, National Chiao Tung University, Hsinchu, Taiwan, R.O.C.

International Journal of Neural Systems
|April 1, 1997
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

Evidence for the Collective Nature of Radial Flow in Pb+Pb Collisions with the ATLAS Detector.

Physical review letters·2026
Same author

Evidence for the Dimuon Decay of the Higgs Boson in pp Collisions with the ATLAS Detector.

Physical review letters·2025
Same author

Evidence for Longitudinally Polarized W Bosons in the Electroweak Production of Same-Sign W Boson Pairs in Association with Two Jets in pp Collisions at sqrt[s]=13  TeV with the ATLAS Detector.

Physical review letters·2025
Same author

[Analysis of disease composition and primary surgical procedures in pediatric secondary glaucoma inpatients: a single-center study].

[Zhonghua yan ke za zhi] Chinese journal of ophthalmology·2023
Same author

[Clinical features of young inpatients with angle-closure glaucoma].

[Zhonghua yan ke za zhi] Chinese journal of ophthalmology·2022
Same author

[Survey on the stunting of children under seven years of age in nine cities of China].

Zhonghua er ke za zhi = Chinese journal of pediatrics·2020
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 the Supervised Adaptive Hamming Net (SAHN) for incremental learning. The Supervised Adaptive Hamming Net efficiently learns from various input patterns and establishes learning bounds.

Area of Science:

  • Artificial Intelligence
  • Machine Learning
  • Neural Networks

Background:

  • Incremental learning systems are crucial for adapting to new data without forgetting previous knowledge.
  • Supervised Adaptive Hamming Net (SAHN) offers a novel approach to incremental learning.
  • Existing models like ARTMAP have limitations in handling multiple-valued inputs.

Purpose of the Study:

  • To introduce and analyze the Supervised Adaptive Hamming Net (SAHN) for incremental learning.
  • To generalize SAHN for multiple-valued input patterns.
  • To derive learning bounds for the P-valued SAHN.

Main Methods:

  • Incorporating multiple-valued logic into the Adaptive Hamming Net (AHN) to create the P-valued SAHN.
  • Analyzing learning properties of the P-valued SAHN.

Related Experiment Videos

  • Deriving an upper bound on the number of epochs for learning input-output pairs.
  • Utilizing thermometer codes to connect P-valued and binary-valued SAHNs.

    • Main Results:

    • The binary-valued SAHN is functionally equivalent to a simplified ARTMAP for many-to-one mappings.
    • The P-valued SAHN effectively handles multiple-valued input patterns.
    • An upper bound on learning epochs for the P-valued SAHN was successfully derived.
    • A connection between P-valued and binary-valued SAHNs was established.

    Conclusions:

    • The Supervised Adaptive Hamming Net (SAHN) provides an effective framework for incremental learning with diverse input types.
    • The derived learning bounds offer theoretical insights into the efficiency of the P-valued SAHN.
    • The generalization to multiple-valued logic enhances the applicability of SAHN in complex pattern recognition tasks.