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 Video

Updated: Mar 25, 2026

Augmenting Large Language Models via Vector Embeddings to Improve Domain-Specific Responsiveness
03:14

Augmenting Large Language Models via Vector Embeddings to Improve Domain-Specific Responsiveness

Published on: December 6, 2024

1.3K

Blind Domain Adaptation With Augmented Extreme Learning Machine Features.

Muhammad Uzair, Ajmal Mian

    IEEE Transactions on Cybernetics
    |February 18, 2016
    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

    Predictors and Outcomes of 30-Day Readmissions Following Electrical Cardioversion for Atrial Fibrillation: Insights From the Nationwide Readmissions Database.

    Journal of arrhythmia·2026
    Same author

    Outcomes of Noninvasive Positive Pressure Ventilation via RAM Cannula in Pediatric Intensive Care: A Preliminary Report.

    International journal of pediatrics·2026
    Same author

    Temporal trends in mortality involving chronic lower respiratory disease and chronic kidney disease: evidence from CDC WONDER, 1999-2023.

    BMC nephrology·2026
    Same author

    Epidemiology and risk factors of surgical site infections in elective surgeries in Pakistan (2022-2023): a multicentre, prospective cohort study from PakSurg 1.

    The Lancet regional health. Southeast Asia·2026
    Same author

    Reach, implementation fidelity, and safety of bubble continuous positive airway pressure (bCPAP) therapy in children with severe pneumonia in Pakistan.

    PLOS global public health·2026
    Same author

    Comparative immune response and disease resistance against Aeromonas hydrophila in Catla catla, Labeo rohita and their intergeneric hybrids.

    Fish & shellfish immunology·2026
    Same journal

    A New Human-Likeness and Comfort Index for Robot Movements Along Prescribed Paths.

    IEEE transactions on cybernetics·2026
    Same journal

    Robust Semiglobal and Global Stabilization for Nonlinear Normal Form Systems by Time-Varying Feedback.

    IEEE transactions on cybernetics·2026
    Same journal

    Adaptive Global Asymptotic Output Stabilization of Uncertain Nonlinear Systems Under Dynamic State/Input Quantization.

    IEEE transactions on cybernetics·2026
    Same journal

    Accelerated Distributed Gradient Tracking for Constrained Aggregative Optimization Over Time-Varying Digraphs.

    IEEE transactions on cybernetics·2026
    Same journal

    Small-Gain-Based Plug-and-Play Distributed Control Framework for DC Microgrids With Decentralized Reconfiguration.

    IEEE transactions on cybernetics·2026
    Same journal

    Prescribed-Time Impulsive Control of High-Order Integrator Systems.

    IEEE transactions on cybernetics·2026
    See all related articles

    This study introduces a blind domain adaptation (DA) method for visual classification. The novel approach enhances features without target domain data, outperforming existing methods.

    Area of Science:

    • Computer Science
    • Artificial Intelligence
    • Machine Learning

    Background:

    • Visual classification performance degrades with mismatched training and testing data distributions.
    • Domain Adaptation (DA) aims to create robust classifiers for such scenarios.
    • Current DA methods often require unlabeled target domain data during training, which is not always feasible.

    Purpose of the Study:

    • To propose a blind Domain Adaptation (DA) algorithm that does not require target domain samples during training.
    • To develop a method for visual classification robust to distribution shifts without access to target domain data.

    Main Methods:

    • Learned an unsupervised global nonlinear Extreme Learning Machine (ELM) model from source domain data.
    • Initialized and trained class-specific ELM models using the global ELM and source data.

    Related Experiment Videos

    Last Updated: Mar 25, 2026

    Augmenting Large Language Models via Vector Embeddings to Improve Domain-Specific Responsiveness
    03:14

    Augmenting Large Language Models via Vector Embeddings to Improve Domain-Specific Responsiveness

    Published on: December 6, 2024

    1.3K
  • Augmented target domain features with reconstructed features from the global ELM model for classification.

    • Main Results:

    • The proposed blind DA method achieved superior performance in cross-domain visual recognition.
    • Outperformed six state-of-the-art methods across 16 standard datasets.
    • Demonstrated effective adaptation without utilizing target domain samples during training.

    Conclusions:

    • Blind DA is a viable approach for visual classification when target domain data is unavailable.
    • The proposed ELM-based method offers a robust solution for domain adaptation challenges.
    • This research advances the field of unsupervised domain adaptation for visual recognition tasks.