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

Bias learning, knowledge sharing.

J Ghosn1, Y Bengio

  • 1Dept. of Informatique et Recherche Operationnelle, Univ. de Montreal, Que., Canada.

IEEE Transactions on Neural Networks
|February 2, 2008
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

Generational perspectives on PrEP, prevention, and sexual practices in MSM (ANRS-PREVENIR cohort).

AIDS care·2025
Same author

Perception of PrEP-related stigma in PrEP users: Results from the ANRS-PREVENIR cohort.

HIV medicine·2023
Same author

Efficacy and tolerability of combined antiretroviral treatment with bictegravir/emtricitabine/tenofovir alafenamide initiated at the time of primary HIV infection.

The Journal of antimicrobial chemotherapy·2021
Same author

How PrEP users constitute a community in the MSM population through their specific experience and management of stigmatization. The example of the French ANRS-PREVENIR study.

AIDS care·2020
Same author

Phylogenetic investigation of HCV-4d epidemic in Paris MSM HIV population reveals a still active outbreak and a strong link to the Netherlands.

Clinical microbiology and infection : the official publication of the European Society of Clinical Microbiology and Infectious Diseases·2020
Same author

First year of pre-exposure prophylaxis implementation in France with daily or on-demand tenofovir disoproxil fumarate/emtricitabine.

The Journal of antimicrobial chemotherapy·2019
Same journal

Universal perceptron and DNA-like learning algorithm for binary neural networks: LSBF and PBF implementations.

IEEE transactions on neural networks·2013
Same journal

Guest editorial: special section on white box nonlinear prediction models.

IEEE transactions on neural networks·2011
Same journal

Data-based fault-tolerant control of high-speed trains with traction/braking notch nonlinearities and actuator failures.

IEEE transactions on neural networks·2011
Same journal

Guest editorial: special section on data-based control, modeling, and optimization.

IEEE transactions on neural networks·2011
Same journal

Neural network-based multiple robot simultaneous localization and mapping.

IEEE transactions on neural networks·2011
Same journal

Data-driven model-free adaptive control for a class of MIMO nonlinear discrete-time systems.

IEEE transactions on neural networks·2011
See all related articles

This study introduces a novel multitask learning approach that learns a hypothesis space manifold to improve generalization. This method leverages domain knowledge from related tasks, significantly boosting model performance.

Area of Science:

  • Machine Learning
  • Artificial Intelligence
  • Statistical Learning Theory

Background:

  • Properly biasing a learner's hypothesis space enhances generalization performance.
  • Existing methods include designing explicit bias or learning bias automatically, with multitask learning falling into the latter category.
  • Multitask learning utilizes domain knowledge from related tasks to inform bias.

Purpose of the Study:

  • To extend multitask learning by introducing a new approach for identifying a family of hypotheses (a manifold) that encodes domain knowledge.
  • To constrain learning models to select hypotheses only from this learned manifold.
  • To demonstrate the versatility and effectiveness of this manifold-based bias learning.

Main Methods:

  • A novel approach is proposed to identify a manifold in hypothesis space representing domain-related knowledge.

Related Experiment Videos

  • This manifold is learned using training examples from a group of related tasks.
  • Learning models are restricted to hypotheses within the learned manifold.

    • Main Results:

    • The proposed approach can learn a wide variety of hypothesis families (manifolds).
    • A statistical analysis on related tasks demonstrates significantly improved performance using this method.
    • The approach effectively incorporates domain knowledge into the learning process.

    Conclusions:

    • The new manifold-based approach offers a powerful way to bias hypothesis spaces in multitask learning.
    • This method enhances generalization by effectively leveraging domain-specific knowledge.
    • The findings suggest significant performance improvements in machine learning tasks through structured bias learning.