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

On learning vector-valued functions.

Charles A Micchelli1, Massimiliano Pontil

  • 1Department of Mathematics and Statistics, State University of New York, University at Albany, Albany, NY, 12222, USA. charles_Micchelli@hotmail.com

Neural Computation
|November 27, 2004
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

The seeds of the future are in the present: A blind exploration of metastable states.

Proceedings of the National Academy of Sciences of the United States of America·2026
Same author

Schedule-Robust Continual Learning.

IEEE transactions on pattern analysis and machine intelligence·2025
Same author

Fast and Fourier features for transfer learning of interatomic potentials.

npj computational materials·2025
Same author

Slow dynamical modes from static averages.

The Journal of chemical physics·2025
Same author

Robust Meta-Representation Learning via Global Label Inference and Classification.

IEEE transactions on pattern analysis and machine intelligence·2023
Same author

Decoding social decisions from movement kinematics.

iScience·2022
Same journal

A Model-Free Reinforcement Learning Implementation of Decision Making Under Uncertainty by Sequential Sampling.

Neural computation·2026
Same journal

DROP: Distributional and Regular Optimism and Pessimism for Reinforcement Learning.

Neural computation·2026
Same journal

Hierarchical Active Inference Using Successor Representations.

Neural computation·2026
Same journal

W-Kernel and Its Principal Space for Frequentist Evaluation of Bayesian Estimators.

Neural computation·2026
Same journal

A Hidden Markov Model-Inspired Sequence Classification Method for Hyperdimensional Computing.

Neural computation·2026
Same journal

Sparse Graphical Modeling for Electrophysiological Phase-Based Connectivity Using Circular Statistics.

Neural computation·2026
See all related articles

This study extends machine learning theory to vector-valued functions in Hilbert spaces. It introduces new methods for multiple-output regularization networks and support vector machines, advancing practical applications.

Area of Science:

  • Machine Learning
  • Functional Analysis
  • Reproducing Kernel Hilbert Spaces

Background:

  • Current machine learning theory primarily addresses scalar-valued functions.
  • Practical applications increasingly require models that handle vector-valued outputs.
  • Extending learning theory to vector-valued functions is crucial for broader applicability.

Purpose of the Study:

  • To extend the theoretical framework of machine learning to vector-valued functions.
  • To establish foundational results for learning in Hilbert spaces of vector-valued functions.
  • To explore applications in multiple-output regularization networks and support vector machines.

Main Methods:

  • Utilizing reproducing kernel Hilbert spaces (RKHS) with vector-valued functions.

Related Experiment Videos

  • Deriving the minimal norm interpolant for finite data sets within this vector-valued RKHS.
  • Analyzing regularization functionals relevant to machine learning theory.

    • Main Results:

    • Established the form of the minimal norm interpolant for vector-valued functions.
    • Applied this to analyze regularization functionals for multiple-output regression and classification.
    • Introduced new operator-valued kernels, including dot product and translation-invariant types.

    Conclusions:

    • The study provides essential theoretical groundwork for vector-valued function learning.
    • The derived methods and kernels are applicable to advanced machine learning models like support vector machines.
    • This work facilitates the development of more sophisticated machine learning systems for complex data outputs.